@claude-flow/cli 3.1.0-alpha.14 โ 3.1.0-alpha.16
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude/helpers/auto-memory-hook.mjs +350 -0
- package/.claude/settings.json +36 -2
- package/README.md +396 -363
- package/dist/src/commands/init.d.ts.map +1 -1
- package/dist/src/commands/init.js +16 -0
- package/dist/src/commands/init.js.map +1 -1
- package/dist/src/init/executor.d.ts.map +1 -1
- package/dist/src/init/executor.js +114 -2
- package/dist/src/init/executor.js.map +1 -1
- package/dist/src/init/settings-generator.d.ts.map +1 -1
- package/dist/src/init/settings-generator.js +30 -0
- package/dist/src/init/settings-generator.js.map +1 -1
- package/dist/src/init/types.d.ts +6 -0
- package/dist/src/init/types.d.ts.map +1 -1
- package/dist/src/init/types.js +6 -0
- package/dist/src/init/types.js.map +1 -1
- package/dist/tsconfig.tsbuildinfo +1 -1
- package/package.json +2 -1
package/README.md
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
|
-
# ๐
|
|
1
|
+
# ๐ Ruflo v3: Enterprise AI Orchestration Platform
|
|
2
2
|
|
|
3
3
|
<div align="center">
|
|
4
4
|
|
|
5
|
-

|
|
6
6
|
|
|
7
7
|
|
|
8
8
|
|
|
9
9
|
[](https://github.com/ruvnet/claude-flow)
|
|
10
|
-
[](https://www.npmjs.com/package/ruflo)
|
|
11
|
+
[](https://www.npmjs.com/package/ruflo)
|
|
12
12
|
[](https://ruv.io)
|
|
13
13
|
[](https://discord.com/invite/dfxmpwkG2D)
|
|
14
14
|
[](https://github.com/ruvnet/claude-flow)
|
|
@@ -25,12 +25,12 @@
|
|
|
25
25
|
|
|
26
26
|
## Getting into the Flow
|
|
27
27
|
|
|
28
|
-
|
|
28
|
+
Ruflo is a comprehensive AI agent orchestration framework that transforms Claude Code into a powerful multi-agent development platform. It enables teams to deploy, coordinate, and optimize specialized AI agents working together on complex software engineering tasks.
|
|
29
29
|
|
|
30
30
|
### Self-Learning/Self-Optimizing Agent Architecture
|
|
31
31
|
|
|
32
32
|
```
|
|
33
|
-
User โ
|
|
33
|
+
User โ Ruflo (CLI/MCP) โ Router โ Swarm โ Agents โ Memory โ LLM Providers
|
|
34
34
|
โ โ
|
|
35
35
|
โโโโโ Learning Loop โโโโโโโโ
|
|
36
36
|
```
|
|
@@ -141,8 +141,8 @@ flowchart TB
|
|
|
141
141
|
# Install RuVector standalone
|
|
142
142
|
npx ruvector
|
|
143
143
|
|
|
144
|
-
# Or use via
|
|
145
|
-
npx
|
|
144
|
+
# Or use via Ruflo
|
|
145
|
+
npx ruflo@v3alpha hooks intelligence --status
|
|
146
146
|
```
|
|
147
147
|
|
|
148
148
|
</details>
|
|
@@ -157,7 +157,7 @@ curl -fsSL https://cdn.jsdelivr.net/gh/ruvnet/claude-flow@main/scripts/install.s
|
|
|
157
157
|
curl -fsSL https://cdn.jsdelivr.net/gh/ruvnet/claude-flow@main/scripts/install.sh | bash -s -- --full
|
|
158
158
|
|
|
159
159
|
# Or via npx
|
|
160
|
-
npx
|
|
160
|
+
npx ruflo@alpha init --wizard
|
|
161
161
|
```
|
|
162
162
|
|
|
163
163
|
---
|
|
@@ -171,7 +171,7 @@ npx claude-flow@alpha init --wizard
|
|
|
171
171
|
|
|
172
172
|
๐ **Works With Any LLM** - Switch between Claude, GPT, Gemini, Cohere, or local models like Llama. Automatic failover if one provider is unavailable. Smart routing picks the cheapest option that meets quality requirements.
|
|
173
173
|
|
|
174
|
-
โก **Plugs Into Claude Code** - Native integration via MCP (Model Context Protocol). Use
|
|
174
|
+
โก **Plugs Into Claude Code** - Native integration via MCP (Model Context Protocol). Use ruflo commands directly in your Claude Code sessions with full tool access.
|
|
175
175
|
|
|
176
176
|
๐ **Production-Ready Security** - Built-in protection against prompt injection, input validation, path traversal prevention, command injection blocking, and safe credential handling.
|
|
177
177
|
|
|
@@ -219,11 +219,14 @@ Agents organize into swarms led by queens that coordinate work, prevent drift, a
|
|
|
219
219
|
<details>
|
|
220
220
|
<summary>๐ง <strong>Intelligence & Memory</strong> โ How the system learns and remembers</summary>
|
|
221
221
|
|
|
222
|
-
The system stores successful patterns in vector memory, learns from outcomes via neural networks, and adapts routing based on what works best.
|
|
222
|
+
The system stores successful patterns in vector memory, builds a knowledge graph for structural understanding, learns from outcomes via neural networks, and adapts routing based on what works best.
|
|
223
223
|
|
|
224
224
|
| Layer | Components | What It Does |
|
|
225
225
|
|-------|------------|--------------|
|
|
226
226
|
| Memory | HNSW, AgentDB, Cache | Stores and retrieves patterns 150x faster |
|
|
227
|
+
| Knowledge Graph | MemoryGraph, PageRank, Communities | Identifies influential insights, detects clusters (ADR-049) |
|
|
228
|
+
| Self-Learning | LearningBridge, SONA, ReasoningBank | Triggers learning from insights, confidence lifecycle (ADR-049) |
|
|
229
|
+
| Agent Scopes | AgentMemoryScope, 3-scope dirs | Per-agent isolation + cross-agent knowledge transfer (ADR-049) |
|
|
227
230
|
| Embeddings | ONNX Runtime, MiniLM | Local vectors without API calls (75x faster) |
|
|
228
231
|
| Learning | SONA, MoE, ReasoningBank | Self-improves from results (<0.05ms adaptation) |
|
|
229
232
|
| Fine-tuning | MicroLoRA, EWC++ | Lightweight adaptation without full retraining |
|
|
@@ -346,7 +349,7 @@ const config = optimizer.getOptimalConfig(agentCount);
|
|
|
346
349
|
<details>
|
|
347
350
|
<summary>๐ก๏ธ <strong>Anti-Drift Swarm Configuration</strong> โ Prevent goal drift in multi-agent work</summary>
|
|
348
351
|
|
|
349
|
-
Complex swarms can drift from their original goals.
|
|
352
|
+
Complex swarms can drift from their original goals. Ruflo V3 includes anti-drift defaults that prevent agents from going off-task.
|
|
350
353
|
|
|
351
354
|
**Recommended Configuration:**
|
|
352
355
|
|
|
@@ -388,18 +391,20 @@ swarm_init({
|
|
|
388
391
|
|
|
389
392
|
</details>
|
|
390
393
|
|
|
391
|
-
### Claude Code: With vs Without
|
|
394
|
+
### Claude Code: With vs Without Ruflo
|
|
392
395
|
|
|
393
|
-
| Capability | Claude Code Alone | Claude Code +
|
|
396
|
+
| Capability | Claude Code Alone | Claude Code + Ruflo |
|
|
394
397
|
|------------|-------------------|---------------------------|
|
|
395
398
|
| **Agent Collaboration** | Agents work in isolation, no shared context | Agents collaborate via swarms with shared memory and consensus |
|
|
396
399
|
| **Coordination** | Manual orchestration between tasks | Queen-led hierarchy with 5 consensus algorithms (Raft, Byzantine, Gossip) |
|
|
397
400
|
| **Hive Mind** | โ Not available | ๐ Queen-led swarms with collective intelligence, 3 queen types, 8 worker types |
|
|
398
401
|
| **Consensus** | โ No multi-agent decisions | Byzantine fault-tolerant voting (f < n/3), weighted, majority |
|
|
399
|
-
| **Memory** | Session-only, no persistence | HNSW vector memory with 150x-12,500x faster retrieval |
|
|
402
|
+
| **Memory** | Session-only, no persistence | HNSW vector memory with 150x-12,500x faster retrieval + knowledge graph |
|
|
400
403
|
| **Vector Database** | โ No native support | ๐ RuVector PostgreSQL with 77+ SQL functions, ~61ยตs search, 16,400 QPS |
|
|
404
|
+
| **Knowledge Graph** | โ Flat insight lists | PageRank + community detection identifies influential insights (ADR-049) |
|
|
401
405
|
| **Collective Memory** | โ No shared knowledge | Shared knowledge base with LRU cache, SQLite persistence, 8 memory types |
|
|
402
|
-
| **Learning** | Static behavior, no adaptation | SONA self-learning with <0.05ms adaptation,
|
|
406
|
+
| **Learning** | Static behavior, no adaptation | SONA self-learning with <0.05ms adaptation, LearningBridge for insights |
|
|
407
|
+
| **Agent Scoping** | Single project scope | 3-scope agent memory (project/local/user) with cross-agent transfer |
|
|
403
408
|
| **Task Routing** | You decide which agent to use | Intelligent routing based on learned patterns (89% accuracy) |
|
|
404
409
|
| **Complex Tasks** | Manual breakdown required | Automatic decomposition across 5 domains (Security, Core, Integration, Support) |
|
|
405
410
|
| **Background Workers** | Nothing runs automatically | 12 context-triggered workers auto-dispatch on file changes, patterns, sessions |
|
|
@@ -475,14 +480,14 @@ curl ... | bash -s -- --full
|
|
|
475
480
|
|
|
476
481
|
```bash
|
|
477
482
|
# Quick start (no install needed)
|
|
478
|
-
npx
|
|
483
|
+
npx ruflo@alpha init
|
|
479
484
|
|
|
480
485
|
# Or install globally
|
|
481
|
-
npm install -g
|
|
482
|
-
|
|
486
|
+
npm install -g ruflo@alpha
|
|
487
|
+
ruflo init
|
|
483
488
|
|
|
484
489
|
# With Bun (faster)
|
|
485
|
-
bunx
|
|
490
|
+
bunx ruflo@alpha init
|
|
486
491
|
```
|
|
487
492
|
|
|
488
493
|
#### Install Profiles
|
|
@@ -494,25 +499,25 @@ bunx claude-flow@alpha init
|
|
|
494
499
|
|
|
495
500
|
```bash
|
|
496
501
|
# Minimal install (skip ML/embeddings)
|
|
497
|
-
npm install -g
|
|
502
|
+
npm install -g ruflo@alpha --omit=optional
|
|
498
503
|
```
|
|
499
504
|
|
|
500
505
|
<details>
|
|
501
506
|
<summary>๐ค <strong>OpenAI Codex CLI Support</strong> โ Full Codex integration with self-learning</summary>
|
|
502
507
|
|
|
503
|
-
|
|
508
|
+
Ruflo supports both **Claude Code** and **OpenAI Codex CLI** via the [@claude-flow/codex](https://www.npmjs.com/package/@claude-flow/codex) package, following the [Agentics Foundation](https://agentics.org) standard.
|
|
504
509
|
|
|
505
510
|
### Quick Start for Codex
|
|
506
511
|
|
|
507
512
|
```bash
|
|
508
513
|
# Initialize for Codex CLI (creates AGENTS.md instead of CLAUDE.md)
|
|
509
|
-
npx
|
|
514
|
+
npx ruflo@alpha init --codex
|
|
510
515
|
|
|
511
516
|
# Full Codex setup with all 137+ skills
|
|
512
|
-
npx
|
|
517
|
+
npx ruflo@alpha init --codex --full
|
|
513
518
|
|
|
514
519
|
# Initialize for both platforms (dual mode)
|
|
515
|
-
npx
|
|
520
|
+
npx ruflo@alpha init --dual
|
|
516
521
|
```
|
|
517
522
|
|
|
518
523
|
### Platform Comparison
|
|
@@ -570,16 +575,16 @@ wait # Wait for all to complete
|
|
|
570
575
|
|
|
571
576
|
```bash
|
|
572
577
|
# List collaboration templates
|
|
573
|
-
npx
|
|
578
|
+
npx ruflo-codex dual templates
|
|
574
579
|
|
|
575
580
|
# Run feature development swarm (architect โ coder โ tester โ reviewer)
|
|
576
|
-
npx
|
|
581
|
+
npx ruflo-codex dual run --template feature --task "Add user auth"
|
|
577
582
|
|
|
578
583
|
# Run security audit swarm (scanner โ analyzer โ fixer)
|
|
579
|
-
npx
|
|
584
|
+
npx ruflo-codex dual run --template security --task "src/auth/"
|
|
580
585
|
|
|
581
586
|
# Run refactoring swarm (analyzer โ planner โ refactorer โ validator)
|
|
582
|
-
npx
|
|
587
|
+
npx ruflo-codex dual run --template refactor --task "src/legacy/"
|
|
583
588
|
```
|
|
584
589
|
|
|
585
590
|
### Pre-Built Collaboration Templates
|
|
@@ -599,7 +604,7 @@ When you run `init --codex`, the MCP server is automatically registered:
|
|
|
599
604
|
codex mcp list
|
|
600
605
|
|
|
601
606
|
# If not present, add manually:
|
|
602
|
-
codex mcp add
|
|
607
|
+
codex mcp add ruflo -- npx ruflo mcp start
|
|
603
608
|
```
|
|
604
609
|
|
|
605
610
|
### Self-Learning Workflow
|
|
@@ -648,43 +653,43 @@ codex mcp add claude-flow -- npx claude-flow mcp start
|
|
|
648
653
|
|
|
649
654
|
```bash
|
|
650
655
|
# Initialize project
|
|
651
|
-
npx
|
|
656
|
+
npx ruflo@alpha init
|
|
652
657
|
|
|
653
658
|
# Start MCP server for Claude Code integration
|
|
654
|
-
npx
|
|
659
|
+
npx ruflo@alpha mcp start
|
|
655
660
|
|
|
656
661
|
# Run a task with agents
|
|
657
|
-
npx
|
|
662
|
+
npx ruflo@alpha --agent coder --task "Implement user authentication"
|
|
658
663
|
|
|
659
664
|
# List available agents
|
|
660
|
-
npx
|
|
665
|
+
npx ruflo@alpha --list
|
|
661
666
|
```
|
|
662
667
|
|
|
663
668
|
### Upgrading
|
|
664
669
|
|
|
665
670
|
```bash
|
|
666
671
|
# Update helpers and statusline (preserves your data)
|
|
667
|
-
npx
|
|
672
|
+
npx ruflo@v3alpha init upgrade
|
|
668
673
|
|
|
669
674
|
# Update AND add any missing skills/agents/commands
|
|
670
|
-
npx
|
|
675
|
+
npx ruflo@v3alpha init upgrade --add-missing
|
|
671
676
|
```
|
|
672
677
|
|
|
673
678
|
The `--add-missing` flag automatically detects and installs new skills, agents, and commands that were added in newer versions, without overwriting your existing customizations.
|
|
674
679
|
|
|
675
680
|
### Claude Code MCP Integration
|
|
676
681
|
|
|
677
|
-
Add
|
|
682
|
+
Add ruflo as an MCP server for seamless integration:
|
|
678
683
|
|
|
679
684
|
```bash
|
|
680
|
-
# Add
|
|
681
|
-
claude mcp add
|
|
685
|
+
# Add ruflo MCP server to Claude Code
|
|
686
|
+
claude mcp add ruflo -- npx -y ruflo@latest mcp start
|
|
682
687
|
|
|
683
688
|
# Verify installation
|
|
684
689
|
claude mcp list
|
|
685
690
|
```
|
|
686
691
|
|
|
687
|
-
Once added, Claude Code can use all 175+
|
|
692
|
+
Once added, Claude Code can use all 175+ ruflo MCP tools directly:
|
|
688
693
|
- `swarm_init` - Initialize agent swarms
|
|
689
694
|
- `agent_spawn` - Spawn specialized agents
|
|
690
695
|
- `memory_search` - Search patterns with HNSW (150x faster)
|
|
@@ -695,13 +700,13 @@ Once added, Claude Code can use all 175+ claude-flow MCP tools directly:
|
|
|
695
700
|
## What is it exactly? Agents that learn, build and work perpetually.
|
|
696
701
|
|
|
697
702
|
<details>
|
|
698
|
-
<summary>๐ <strong>Why
|
|
703
|
+
<summary>๐ <strong>Why Ruflo v3?</strong></summary>
|
|
699
704
|
|
|
700
|
-
|
|
705
|
+
Ruflo v3 introduces **self-learning neural capabilities** that no other agent orchestration framework offers. While competitors require manual agent configuration and static routing, Ruflo learns from every task execution, prevents catastrophic forgetting of successful patterns, and intelligently routes work to specialized experts.
|
|
701
706
|
|
|
702
707
|
#### ๐ง Neural & Learning
|
|
703
708
|
|
|
704
|
-
| Feature |
|
|
709
|
+
| Feature | Ruflo v3 | CrewAI | LangGraph | AutoGen | Manus |
|
|
705
710
|
|---------|----------------|--------|-----------|---------|-------|
|
|
706
711
|
| **Self-Learning** | โ
SONA + EWC++ | โ | โ | โ | โ |
|
|
707
712
|
| **Prevents Forgetting** | โ
EWC++ consolidation | โ | โ | โ | โ |
|
|
@@ -712,9 +717,12 @@ Claude-Flow v3 introduces **self-learning neural capabilities** that no other ag
|
|
|
712
717
|
|
|
713
718
|
#### ๐พ Memory & Embeddings
|
|
714
719
|
|
|
715
|
-
| Feature |
|
|
720
|
+
| Feature | Ruflo v3 | CrewAI | LangGraph | AutoGen | Manus |
|
|
716
721
|
|---------|----------------|--------|-----------|---------|-------|
|
|
717
722
|
| **Vector Memory** | โ
HNSW (150x faster) | โ | Via plugins | โ | โ |
|
|
723
|
+
| **Knowledge Graph** | โ
PageRank + communities | โ | โ | โ | โ |
|
|
724
|
+
| **Self-Learning Memory** | โ
LearningBridge (SONA) | โ | โ | โ | โ |
|
|
725
|
+
| **Agent-Scoped Memory** | โ
3-scope (project/local/user) | โ | โ | โ | โ |
|
|
718
726
|
| **PostgreSQL Vector DB** | โ
RuVector (77+ SQL functions, ~61ยตs) | โ | pgvector only | โ | โ |
|
|
719
727
|
| **Hyperbolic Embeddings** | โ
Poincarรฉ ball (native + SQL) | โ | โ | โ | โ |
|
|
720
728
|
| **Quantization** | โ
Int8 (3.92x savings) | โ | โ | โ | โ |
|
|
@@ -724,7 +732,7 @@ Claude-Flow v3 introduces **self-learning neural capabilities** that no other ag
|
|
|
724
732
|
|
|
725
733
|
#### ๐ Swarm & Coordination
|
|
726
734
|
|
|
727
|
-
| Feature |
|
|
735
|
+
| Feature | Ruflo v3 | CrewAI | LangGraph | AutoGen | Manus |
|
|
728
736
|
|---------|----------------|--------|-----------|---------|-------|
|
|
729
737
|
| **Swarm Topologies** | โ
4 types | 1 | 1 | 1 | 1 |
|
|
730
738
|
| **Consensus Protocols** | โ
5 (Raft, BFT, etc.) | โ | โ | โ | โ |
|
|
@@ -734,7 +742,7 @@ Claude-Flow v3 introduces **self-learning neural capabilities** that no other ag
|
|
|
734
742
|
|
|
735
743
|
#### ๐ง Developer Experience
|
|
736
744
|
|
|
737
|
-
| Feature |
|
|
745
|
+
| Feature | Ruflo v3 | CrewAI | LangGraph | AutoGen | Manus |
|
|
738
746
|
|---------|----------------|--------|-----------|---------|-------|
|
|
739
747
|
| **MCP Integration** | โ
Native (170+ tools) | โ | โ | โ | โ |
|
|
740
748
|
| **Skills System** | โ
42+ pre-built | โ | โ | โ | Limited |
|
|
@@ -744,7 +752,7 @@ Claude-Flow v3 introduces **self-learning neural capabilities** that no other ag
|
|
|
744
752
|
|
|
745
753
|
#### ๐ก๏ธ Security & Platform
|
|
746
754
|
|
|
747
|
-
| Feature |
|
|
755
|
+
| Feature | Ruflo v3 | CrewAI | LangGraph | AutoGen | Manus |
|
|
748
756
|
|---------|----------------|--------|-----------|---------|-------|
|
|
749
757
|
| **Threat Detection** | โ
AIDefence (<10ms) | โ | โ | โ | โ |
|
|
750
758
|
| **Cloud Platform** | โ
Flow Nexus | โ | โ | โ | โ |
|
|
@@ -758,7 +766,7 @@ Claude-Flow v3 introduces **self-learning neural capabilities** that no other ag
|
|
|
758
766
|
<details>
|
|
759
767
|
<summary>๐ <strong>Key Differentiators</strong> โ Self-learning, memory optimization, fault tolerance</summary>
|
|
760
768
|
|
|
761
|
-
What makes
|
|
769
|
+
What makes Ruflo different from other agent frameworks? These 10 capabilities work together to create a system that learns from experience, runs efficiently on any hardware, and keeps working even when things go wrong.
|
|
762
770
|
|
|
763
771
|
| | Feature | What It Does | Technical Details |
|
|
764
772
|
|---|---------|--------------|-------------------|
|
|
@@ -778,7 +786,7 @@ What makes Claude-Flow different from other agent frameworks? These 10 capabilit
|
|
|
778
786
|
<details>
|
|
779
787
|
<summary>๐ฐ <strong>Intelligent 3-Tier Model Routing</strong> โ Save 75% on API costs, extend Claude Max 2.5x</summary>
|
|
780
788
|
|
|
781
|
-
Not every task needs the most powerful (and expensive) model.
|
|
789
|
+
Not every task needs the most powerful (and expensive) model. Ruflo analyzes each request and automatically routes it to the cheapest handler that can do the job well. Simple code transforms skip the LLM entirely using WebAssembly. Medium tasks use faster, cheaper models. Only complex architecture decisions use Opus.
|
|
782
790
|
|
|
783
791
|
**Cost & Usage Benefits:**
|
|
784
792
|
|
|
@@ -804,7 +812,7 @@ Not every task needs the most powerful (and expensive) model. Claude-Flow analyz
|
|
|
804
812
|
<details>
|
|
805
813
|
<summary>๐ <strong>Spec-Driven Development</strong> โ Build complete specs, implement without drift</summary>
|
|
806
814
|
|
|
807
|
-
Complex projects fail when implementation drifts from the original plan.
|
|
815
|
+
Complex projects fail when implementation drifts from the original plan. Ruflo solves this with a spec-first approach: define your architecture through ADRs (Architecture Decision Records), organize code into DDD bounded contexts, and let the system enforce compliance as agents work. The result is implementations that match specifications โ even across multi-agent swarms working in parallel.
|
|
808
816
|
|
|
809
817
|
**How It Prevents Drift:**
|
|
810
818
|
|
|
@@ -847,6 +855,8 @@ Complex projects fail when implementation drifts from the original plan. Claude-
|
|
|
847
855
|
- **ADR-008**: Vitest testing framework (10x faster than Jest)
|
|
848
856
|
- **ADR-009**: Hybrid Memory Backend (SQLite + HNSW)
|
|
849
857
|
- **ADR-026**: Intelligent 3-tier model routing
|
|
858
|
+
- **ADR-048**: Auto Memory Bridge (Claude Code โ AgentDB bidirectional sync)
|
|
859
|
+
- **ADR-049**: Self-Learning Memory with GNN (LearningBridge, MemoryGraph, AgentMemoryScope)
|
|
850
860
|
|
|
851
861
|
</details>
|
|
852
862
|
|
|
@@ -943,28 +953,32 @@ sequenceDiagram
|
|
|
943
953
|
</details>
|
|
944
954
|
|
|
945
955
|
<details>
|
|
946
|
-
<summary>๐ง <strong>Memory Architecture</strong> โ How knowledge is stored and retrieved</summary>
|
|
956
|
+
<summary>๐ง <strong>Memory Architecture</strong> โ How knowledge is stored, learned, and retrieved</summary>
|
|
947
957
|
|
|
948
958
|
```mermaid
|
|
949
959
|
flowchart LR
|
|
950
960
|
subgraph Input["๐ฅ Input"]
|
|
951
961
|
Query[Query/Pattern]
|
|
962
|
+
Insight[New Insight]
|
|
952
963
|
end
|
|
953
964
|
|
|
954
965
|
subgraph Processing["โ๏ธ Processing"]
|
|
955
966
|
Embed[ONNX Embeddings]
|
|
956
967
|
Normalize[Normalization]
|
|
968
|
+
Learn[LearningBridge<br/>SONA + ReasoningBank]
|
|
957
969
|
end
|
|
958
970
|
|
|
959
971
|
subgraph Storage["๐พ Storage"]
|
|
960
972
|
HNSW[(HNSW Index<br/>150x faster)]
|
|
961
973
|
SQLite[(SQLite Cache)]
|
|
962
974
|
AgentDB[(AgentDB)]
|
|
975
|
+
Graph[MemoryGraph<br/>PageRank + Communities]
|
|
963
976
|
end
|
|
964
977
|
|
|
965
978
|
subgraph Retrieval["๐ Retrieval"]
|
|
966
979
|
Vector[Vector Search]
|
|
967
980
|
Semantic[Semantic Match]
|
|
981
|
+
Rank[Graph-Aware Ranking]
|
|
968
982
|
Results[Top-K Results]
|
|
969
983
|
end
|
|
970
984
|
|
|
@@ -972,13 +986,26 @@ flowchart LR
|
|
|
972
986
|
Embed --> Normalize
|
|
973
987
|
Normalize --> HNSW
|
|
974
988
|
Normalize --> SQLite
|
|
989
|
+
Insight --> Learn
|
|
990
|
+
Learn --> AgentDB
|
|
991
|
+
AgentDB --> Graph
|
|
975
992
|
HNSW --> Vector
|
|
976
993
|
SQLite --> Vector
|
|
977
994
|
AgentDB --> Semantic
|
|
978
|
-
Vector -->
|
|
979
|
-
Semantic -->
|
|
995
|
+
Vector --> Rank
|
|
996
|
+
Semantic --> Rank
|
|
997
|
+
Graph --> Rank
|
|
998
|
+
Rank --> Results
|
|
980
999
|
```
|
|
981
1000
|
|
|
1001
|
+
**Self-Learning Memory (ADR-049):**
|
|
1002
|
+
| Component | Purpose | Performance |
|
|
1003
|
+
|-----------|---------|-------------|
|
|
1004
|
+
| **LearningBridge** | Connects insights to SONA/ReasoningBank neural pipeline | 0.12 ms/insight |
|
|
1005
|
+
| **MemoryGraph** | PageRank + label propagation knowledge graph | 2.78 ms build (1k nodes) |
|
|
1006
|
+
| **AgentMemoryScope** | 3-scope agent memory (project/local/user) with cross-agent transfer | 1.25 ms transfer |
|
|
1007
|
+
| **AutoMemoryBridge** | Bidirectional sync: Claude Code auto memory files โ AgentDB | ADR-048 |
|
|
1008
|
+
|
|
982
1009
|
</details>
|
|
983
1010
|
|
|
984
1011
|
<details>
|
|
@@ -1051,18 +1078,18 @@ flowchart TB
|
|
|
1051
1078
|
|
|
1052
1079
|
## ๐ Setup & Configuration
|
|
1053
1080
|
|
|
1054
|
-
Connect
|
|
1081
|
+
Connect Ruflo to your development environment.
|
|
1055
1082
|
|
|
1056
1083
|
<details>
|
|
1057
|
-
<summary>๐ <strong>MCP Setup</strong> โ Connect
|
|
1084
|
+
<summary>๐ <strong>MCP Setup</strong> โ Connect Ruflo to Any AI Environment</summary>
|
|
1058
1085
|
|
|
1059
|
-
|
|
1086
|
+
Ruflo runs as an MCP (Model Context Protocol) server, allowing you to connect it to any MCP-compatible AI client. This means you can use Ruflo's 60+ agents, swarm coordination, and self-learning capabilities from Claude Desktop, VS Code, Cursor, Windsurf, ChatGPT, and more.
|
|
1060
1087
|
|
|
1061
1088
|
### Quick Add Command
|
|
1062
1089
|
|
|
1063
1090
|
```bash
|
|
1064
|
-
# Start
|
|
1065
|
-
npx
|
|
1091
|
+
# Start Ruflo MCP server in any environment
|
|
1092
|
+
npx ruflo@v3alpha mcp start
|
|
1066
1093
|
```
|
|
1067
1094
|
|
|
1068
1095
|
<details open>
|
|
@@ -1077,9 +1104,9 @@ npx claude-flow@v3alpha mcp start
|
|
|
1077
1104
|
```json
|
|
1078
1105
|
{
|
|
1079
1106
|
"mcpServers": {
|
|
1080
|
-
"
|
|
1107
|
+
"ruflo": {
|
|
1081
1108
|
"command": "npx",
|
|
1082
|
-
"args": ["
|
|
1109
|
+
"args": ["ruflo@v3alpha", "mcp", "start"],
|
|
1083
1110
|
"env": {
|
|
1084
1111
|
"ANTHROPIC_API_KEY": "sk-ant-..."
|
|
1085
1112
|
}
|
|
@@ -1099,12 +1126,12 @@ Restart Claude Desktop after saving. Look for the MCP indicator (hammer icon) in
|
|
|
1099
1126
|
|
|
1100
1127
|
```bash
|
|
1101
1128
|
# Add via CLI (recommended)
|
|
1102
|
-
claude mcp add
|
|
1129
|
+
claude mcp add ruflo -- npx ruflo@v3alpha mcp start
|
|
1103
1130
|
|
|
1104
1131
|
# Or add with environment variables
|
|
1105
|
-
claude mcp add
|
|
1132
|
+
claude mcp add ruflo \
|
|
1106
1133
|
--env ANTHROPIC_API_KEY=sk-ant-... \
|
|
1107
|
-
-- npx
|
|
1134
|
+
-- npx ruflo@v3alpha mcp start
|
|
1108
1135
|
|
|
1109
1136
|
# Verify installation
|
|
1110
1137
|
claude mcp list
|
|
@@ -1131,9 +1158,9 @@ Create `.vscode/mcp.json` in your project:
|
|
|
1131
1158
|
```json
|
|
1132
1159
|
{
|
|
1133
1160
|
"mcpServers": {
|
|
1134
|
-
"
|
|
1161
|
+
"ruflo": {
|
|
1135
1162
|
"command": "npx",
|
|
1136
|
-
"args": ["
|
|
1163
|
+
"args": ["ruflo@v3alpha", "mcp", "start"],
|
|
1137
1164
|
"env": {
|
|
1138
1165
|
"ANTHROPIC_API_KEY": "sk-ant-..."
|
|
1139
1166
|
}
|
|
@@ -1158,9 +1185,9 @@ Create `.cursor/mcp.json` in your project (or global config):
|
|
|
1158
1185
|
```json
|
|
1159
1186
|
{
|
|
1160
1187
|
"mcpServers": {
|
|
1161
|
-
"
|
|
1188
|
+
"ruflo": {
|
|
1162
1189
|
"command": "npx",
|
|
1163
|
-
"args": ["
|
|
1190
|
+
"args": ["ruflo@v3alpha", "mcp", "start"],
|
|
1164
1191
|
"env": {
|
|
1165
1192
|
"ANTHROPIC_API_KEY": "sk-ant-..."
|
|
1166
1193
|
}
|
|
@@ -1185,9 +1212,9 @@ Create `.cursor/mcp.json` in your project (or global config):
|
|
|
1185
1212
|
```json
|
|
1186
1213
|
{
|
|
1187
1214
|
"mcpServers": {
|
|
1188
|
-
"
|
|
1215
|
+
"ruflo": {
|
|
1189
1216
|
"command": "npx",
|
|
1190
|
-
"args": ["
|
|
1217
|
+
"args": ["ruflo@v3alpha", "mcp", "start"],
|
|
1191
1218
|
"env": {
|
|
1192
1219
|
"ANTHROPIC_API_KEY": "sk-ant-..."
|
|
1193
1220
|
}
|
|
@@ -1214,11 +1241,11 @@ Click **Refresh** in the MCP settings to connect. Windsurf supports up to 100 MC
|
|
|
1214
1241
|
|
|
1215
1242
|
**Remote Server Setup:**
|
|
1216
1243
|
|
|
1217
|
-
For ChatGPT, you need a remote MCP server (not local stdio). Deploy
|
|
1244
|
+
For ChatGPT, you need a remote MCP server (not local stdio). Deploy ruflo to a server with HTTP transport:
|
|
1218
1245
|
|
|
1219
1246
|
```bash
|
|
1220
1247
|
# Start with HTTP transport
|
|
1221
|
-
npx
|
|
1248
|
+
npx ruflo@v3alpha mcp start --transport http --port 3000
|
|
1222
1249
|
```
|
|
1223
1250
|
|
|
1224
1251
|
Then add the server URL in ChatGPT Connectors settings.
|
|
@@ -1234,7 +1261,7 @@ Google AI Studio supports MCP natively since May 2025, with managed MCP servers
|
|
|
1234
1261
|
|
|
1235
1262
|
**Using MCP SuperAssistant Extension:**
|
|
1236
1263
|
1. Install [MCP SuperAssistant](https://chrome.google.com/webstore) Chrome extension
|
|
1237
|
-
2. Configure your
|
|
1264
|
+
2. Configure your ruflo MCP server
|
|
1238
1265
|
3. Use with Google AI Studio, Gemini, and other AI platforms
|
|
1239
1266
|
|
|
1240
1267
|
**Native SDK Integration:**
|
|
@@ -1247,9 +1274,9 @@ const ai = new GoogleGenAI({ apiKey: 'YOUR_API_KEY' });
|
|
|
1247
1274
|
// MCP definitions are natively supported in the Gen AI SDK
|
|
1248
1275
|
const mcpConfig = {
|
|
1249
1276
|
servers: [{
|
|
1250
|
-
name: '
|
|
1277
|
+
name: 'ruflo',
|
|
1251
1278
|
command: 'npx',
|
|
1252
|
-
args: ['
|
|
1279
|
+
args: ['ruflo@v3alpha', 'mcp', 'start']
|
|
1253
1280
|
}]
|
|
1254
1281
|
};
|
|
1255
1282
|
```
|
|
@@ -1270,9 +1297,9 @@ JetBrains AI Assistant supports MCP for IntelliJ IDEA, PyCharm, WebStorm, and ot
|
|
|
1270
1297
|
|
|
1271
1298
|
```json
|
|
1272
1299
|
{
|
|
1273
|
-
"name": "
|
|
1300
|
+
"name": "ruflo",
|
|
1274
1301
|
"command": "npx",
|
|
1275
|
-
"args": ["
|
|
1302
|
+
"args": ["ruflo@v3alpha", "mcp", "start"]
|
|
1276
1303
|
}
|
|
1277
1304
|
```
|
|
1278
1305
|
|
|
@@ -1502,13 +1529,13 @@ The Hive Mind system implements queen-led hierarchical coordination where strate
|
|
|
1502
1529
|
|
|
1503
1530
|
**CLI Commands:**
|
|
1504
1531
|
```bash
|
|
1505
|
-
npx
|
|
1506
|
-
npx
|
|
1507
|
-
npx
|
|
1508
|
-
npx
|
|
1509
|
-
npx
|
|
1510
|
-
npx
|
|
1511
|
-
npx
|
|
1532
|
+
npx ruflo hive-mind init # Initialize hive mind
|
|
1533
|
+
npx ruflo hive-mind spawn "Build API" # Spawn with objective
|
|
1534
|
+
npx ruflo hive-mind spawn "..." --queen-type strategic --consensus byzantine
|
|
1535
|
+
npx ruflo hive-mind status # Check status
|
|
1536
|
+
npx ruflo hive-mind metrics # Performance metrics
|
|
1537
|
+
npx ruflo hive-mind memory # Collective memory stats
|
|
1538
|
+
npx ruflo hive-mind sessions # List active sessions
|
|
1512
1539
|
```
|
|
1513
1540
|
|
|
1514
1541
|
**Performance:** 10-20x faster batch spawning, 2.8-4.4x speed improvement, 84.8% SWE-Bench solve rate
|
|
@@ -1522,8 +1549,8 @@ Native integration with Claude Code's experimental Agent Teams feature for spawn
|
|
|
1522
1549
|
|
|
1523
1550
|
**Enable Agent Teams:**
|
|
1524
1551
|
```bash
|
|
1525
|
-
# Automatically enabled with
|
|
1526
|
-
npx
|
|
1552
|
+
# Automatically enabled with ruflo init
|
|
1553
|
+
npx ruflo@latest init
|
|
1527
1554
|
|
|
1528
1555
|
# Or manually add to .claude/settings.json
|
|
1529
1556
|
{
|
|
@@ -1575,10 +1602,10 @@ TeamDelete()
|
|
|
1575
1602
|
|
|
1576
1603
|
```bash
|
|
1577
1604
|
# Handle idle teammate
|
|
1578
|
-
npx
|
|
1605
|
+
npx ruflo@latest hooks teammate-idle --auto-assign true
|
|
1579
1606
|
|
|
1580
1607
|
# Handle task completion
|
|
1581
|
-
npx
|
|
1608
|
+
npx ruflo@latest hooks task-completed --task-id <id> --train-patterns
|
|
1582
1609
|
```
|
|
1583
1610
|
|
|
1584
1611
|
**Display Modes:** `auto` (default), `in-process`, `tmux` (split-pane)
|
|
@@ -1655,14 +1682,14 @@ Build custom plugins with the fluent builder API. Create MCP tools, hooks, worke
|
|
|
1655
1682
|
|
|
1656
1683
|
### ๐ฆ Available Optional Plugins
|
|
1657
1684
|
|
|
1658
|
-
Install these optional plugins to extend
|
|
1685
|
+
Install these optional plugins to extend Ruflo capabilities:
|
|
1659
1686
|
|
|
1660
1687
|
| Plugin | Version | Description | Install Command |
|
|
1661
1688
|
|--------|---------|-------------|-----------------|
|
|
1662
1689
|
| **@claude-flow/plugin-agentic-qe** | 3.0.0-alpha.2 | Quality Engineering with 58 AI agents across 12 DDD contexts. TDD, coverage analysis, security scanning, chaos engineering, accessibility testing. | `npm install @claude-flow/plugin-agentic-qe` |
|
|
1663
1690
|
| **@claude-flow/plugin-prime-radiant** | 0.1.4 | Mathematical AI interpretability with 6 engines: sheaf cohomology, spectral analysis, causal inference, quantum topology, category theory, HoTT proofs. | `npm install @claude-flow/plugin-prime-radiant` |
|
|
1664
|
-
| **@claude-flow/plugin-gastown-bridge** | 0.1.0 | Gas Town orchestrator integration with WASM-accelerated formula parsing (352x faster), Beads sync, convoy management, and graph analysis. 20 MCP tools. | `npx
|
|
1665
|
-
| **@claude-flow/teammate-plugin** | 1.0.0-alpha.1 | Native TeammateTool integration for Claude Code v2.1.19+. BMSSP WASM acceleration, rate limiting, circuit breaker, semantic routing. 21 MCP tools. | `npx
|
|
1691
|
+
| **@claude-flow/plugin-gastown-bridge** | 0.1.0 | Gas Town orchestrator integration with WASM-accelerated formula parsing (352x faster), Beads sync, convoy management, and graph analysis. 20 MCP tools. | `npx ruflo@latest plugins install -n @claude-flow/plugin-gastown-bridge` |
|
|
1692
|
+
| **@claude-flow/teammate-plugin** | 1.0.0-alpha.1 | Native TeammateTool integration for Claude Code v2.1.19+. BMSSP WASM acceleration, rate limiting, circuit breaker, semantic routing. 21 MCP tools. | `npx ruflo@latest plugins install -n @claude-flow/teammate-plugin` |
|
|
1666
1693
|
|
|
1667
1694
|
#### ๐ฅ Domain-Specific Plugins
|
|
1668
1695
|
|
|
@@ -1732,7 +1759,7 @@ npm install @claude-flow/plugin-agentic-qe
|
|
|
1732
1759
|
npm install @claude-flow/plugin-prime-radiant
|
|
1733
1760
|
|
|
1734
1761
|
# Install Gas Town Bridge plugin (WASM-accelerated orchestration)
|
|
1735
|
-
npx
|
|
1762
|
+
npx ruflo@latest plugins install -n @claude-flow/plugin-gastown-bridge
|
|
1736
1763
|
|
|
1737
1764
|
# Install domain-specific plugins
|
|
1738
1765
|
npm install @claude-flow/plugin-healthcare-clinical
|
|
@@ -1751,7 +1778,7 @@ npm install @claude-flow/plugin-quantum-optimizer
|
|
|
1751
1778
|
npm install @claude-flow/plugin-hyperbolic-reasoning
|
|
1752
1779
|
|
|
1753
1780
|
# List all installed plugins
|
|
1754
|
-
npx
|
|
1781
|
+
npx ruflo plugins list --installed
|
|
1755
1782
|
```
|
|
1756
1783
|
|
|
1757
1784
|
</details>
|
|
@@ -1920,8 +1947,8 @@ Workers run automatically based on context, or dispatch manually via MCP tools.
|
|
|
1920
1947
|
| **TestGaps** | `testgaps` | Test coverage analysis | Code changes without tests |
|
|
1921
1948
|
|
|
1922
1949
|
```bash
|
|
1923
|
-
npx
|
|
1924
|
-
npx
|
|
1950
|
+
npx ruflo@v3alpha worker dispatch --trigger audit --context "./src"
|
|
1951
|
+
npx ruflo@v3alpha worker status
|
|
1925
1952
|
```
|
|
1926
1953
|
|
|
1927
1954
|
</details>
|
|
@@ -2145,7 +2172,7 @@ npx claude-flow@v3alpha worker status
|
|
|
2145
2172
|
| Feature | Description | Performance |
|
|
2146
2173
|
|---------|-------------|-------------|
|
|
2147
2174
|
| **Multi-Provider** | Agentic-Flow (ONNX), OpenAI, Transformers.js, Mock | 4 providers |
|
|
2148
|
-
| **Auto-Install** | `
|
|
2175
|
+
| **Auto-Install** | `ruflo embeddings init` or `createEmbeddingServiceAsync()` | Zero config |
|
|
2149
2176
|
| **75x Faster** | Agentic-flow ONNX SIMD vs Transformers.js | 3ms vs 230ms |
|
|
2150
2177
|
| **Hyperbolic Space** | Poincarรฉ ball model for hierarchical data | Exponential capacity |
|
|
2151
2178
|
| **Dimensions** | 384 to 3072 configurable | Quality vs speed tradeoff |
|
|
@@ -2155,13 +2182,13 @@ npx claude-flow@v3alpha worker status
|
|
|
2155
2182
|
|
|
2156
2183
|
```bash
|
|
2157
2184
|
# Initialize ONNX embeddings with hyperbolic config
|
|
2158
|
-
|
|
2185
|
+
ruflo embeddings init
|
|
2159
2186
|
|
|
2160
2187
|
# Use larger model for higher quality
|
|
2161
|
-
|
|
2188
|
+
ruflo embeddings init --model all-mpnet-base-v2
|
|
2162
2189
|
|
|
2163
2190
|
# Semantic search
|
|
2164
|
-
|
|
2191
|
+
ruflo embeddings search -q "authentication patterns"
|
|
2165
2192
|
```
|
|
2166
2193
|
|
|
2167
2194
|
| Mode | Adaptation | Quality | Memory | Use Case |
|
|
@@ -2198,22 +2225,22 @@ claude-flow embeddings search -q "authentication patterns"
|
|
|
2198
2225
|
|
|
2199
2226
|
```bash
|
|
2200
2227
|
# Initialize RuVector in PostgreSQL
|
|
2201
|
-
|
|
2228
|
+
ruflo ruvector init --database mydb --user admin
|
|
2202
2229
|
|
|
2203
2230
|
# Check connection and schema status
|
|
2204
|
-
|
|
2231
|
+
ruflo ruvector status --verbose
|
|
2205
2232
|
|
|
2206
2233
|
# Run pending migrations
|
|
2207
|
-
|
|
2234
|
+
ruflo ruvector migrate --up
|
|
2208
2235
|
|
|
2209
2236
|
# Performance benchmark
|
|
2210
|
-
|
|
2237
|
+
ruflo ruvector benchmark --iterations 1000
|
|
2211
2238
|
|
|
2212
2239
|
# Optimize indices and vacuum
|
|
2213
|
-
|
|
2240
|
+
ruflo ruvector optimize --analyze
|
|
2214
2241
|
|
|
2215
2242
|
# Backup vector data
|
|
2216
|
-
|
|
2243
|
+
ruflo ruvector backup --output ./backup.sql
|
|
2217
2244
|
```
|
|
2218
2245
|
|
|
2219
2246
|
| Migration | Purpose | Features |
|
|
@@ -2245,13 +2272,13 @@ claude-flow ruvector backup --output ./backup.sql
|
|
|
2245
2272
|
|
|
2246
2273
|
**Quick Commands:**
|
|
2247
2274
|
```bash
|
|
2248
|
-
npx
|
|
2249
|
-
npx
|
|
2250
|
-
npx
|
|
2251
|
-
npx
|
|
2275
|
+
npx ruflo hive-mind init # Initialize
|
|
2276
|
+
npx ruflo hive-mind spawn "Build API" --queen-type tactical # Spawn swarm
|
|
2277
|
+
npx ruflo hive-mind spawn "Research AI" --consensus byzantine --claude
|
|
2278
|
+
npx ruflo hive-mind status # Check status
|
|
2252
2279
|
```
|
|
2253
2280
|
|
|
2254
|
-
**
|
|
2281
|
+
**Ruflo Skill:** `/hive-mind-advanced` โ Full hive mind orchestration
|
|
2255
2282
|
|
|
2256
2283
|
**Performance:** 10-20x faster batch spawning, 84.8% SWE-Bench solve rate, 32.3% token reduction
|
|
2257
2284
|
|
|
@@ -2363,7 +2390,7 @@ Real-time development status display for Claude Code integration showing DDD pro
|
|
|
2363
2390
|
|
|
2364
2391
|
**Output Format:**
|
|
2365
2392
|
```
|
|
2366
|
-
โ
|
|
2393
|
+
โ Ruflo V3 โ ruvnet โ โ v3 โ Opus 4.5
|
|
2367
2394
|
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
|
|
2368
2395
|
๐๏ธ DDD Domains [โโโโโ] 5/5 โก 1.0x โ 2.49x-7.47x
|
|
2369
2396
|
๐ค Swarm โ [58/15] ๐ฅ 0 ๐ข CVE 3/3 ๐พ 22282MB ๐ 47% ๐ง 10%
|
|
@@ -2372,7 +2399,7 @@ Real-time development status display for Claude Code integration showing DDD pro
|
|
|
2372
2399
|
|
|
2373
2400
|
| Indicator | Description | Values |
|
|
2374
2401
|
|-----------|-------------|--------|
|
|
2375
|
-
| `โ
|
|
2402
|
+
| `โ Ruflo V3` | Project header | Always shown |
|
|
2376
2403
|
| `โ ruvnet` | GitHub user (via `gh` CLI) | Dynamic |
|
|
2377
2404
|
| `โ v3` | Current git branch | Dynamic |
|
|
2378
2405
|
| `Opus 4.5` | Claude model name | From Claude Code |
|
|
@@ -2393,19 +2420,19 @@ Real-time development status display for Claude Code integration showing DDD pro
|
|
|
2393
2420
|
**Usage:**
|
|
2394
2421
|
```bash
|
|
2395
2422
|
# Default: Safe multi-line (avoids Claude Code collision zone)
|
|
2396
|
-
npx
|
|
2423
|
+
npx ruflo@v3alpha hooks statusline
|
|
2397
2424
|
|
|
2398
2425
|
# Single-line mode (completely avoids collision)
|
|
2399
|
-
npx
|
|
2426
|
+
npx ruflo@v3alpha hooks statusline --single
|
|
2400
2427
|
|
|
2401
2428
|
# Legacy multi-line (original behavior, may have bleeding)
|
|
2402
|
-
npx
|
|
2429
|
+
npx ruflo@v3alpha hooks statusline --legacy
|
|
2403
2430
|
|
|
2404
2431
|
# JSON output for scripting
|
|
2405
|
-
npx
|
|
2432
|
+
npx ruflo@v3alpha hooks statusline --json
|
|
2406
2433
|
|
|
2407
2434
|
# Compact JSON (single line)
|
|
2408
|
-
npx
|
|
2435
|
+
npx ruflo@v3alpha hooks statusline --compact
|
|
2409
2436
|
```
|
|
2410
2437
|
|
|
2411
2438
|
**Collision Zone Fix (Issue #985):**
|
|
@@ -2427,16 +2454,16 @@ Add to `.claude/settings.json`:
|
|
|
2427
2454
|
{
|
|
2428
2455
|
"statusLine": {
|
|
2429
2456
|
"type": "command",
|
|
2430
|
-
"command": "npx
|
|
2457
|
+
"command": "npx ruflo@v3alpha hooks statusline --single"
|
|
2431
2458
|
}
|
|
2432
2459
|
}
|
|
2433
2460
|
```
|
|
2434
2461
|
|
|
2435
2462
|
**Data Sources:**
|
|
2436
|
-
- `.
|
|
2437
|
-
- `.
|
|
2438
|
-
- `.
|
|
2439
|
-
- `.
|
|
2463
|
+
- `.ruflo/metrics/v3-progress.json` - DDD domain progress
|
|
2464
|
+
- `.ruflo/metrics/swarm-activity.json` - Active agent counts
|
|
2465
|
+
- `.ruflo/security/audit-status.json` - CVE remediation status
|
|
2466
|
+
- `.ruflo/learning/patterns.db` - Intelligence score (pattern count)
|
|
2440
2467
|
- Process detection via `ps aux` - Real-time memory and agent counts
|
|
2441
2468
|
- Git branch via `git branch --show-current`
|
|
2442
2469
|
- GitHub user via `gh api user`
|
|
@@ -2461,19 +2488,19 @@ Cross-platform TypeScript-based daemon service with auto-scheduling:
|
|
|
2461
2488
|
**Commands:**
|
|
2462
2489
|
```bash
|
|
2463
2490
|
# Start daemon (auto-runs on SessionStart hooks)
|
|
2464
|
-
npx
|
|
2491
|
+
npx ruflo@v3alpha daemon start
|
|
2465
2492
|
|
|
2466
2493
|
# Check status with worker history
|
|
2467
|
-
npx
|
|
2494
|
+
npx ruflo@v3alpha daemon status
|
|
2468
2495
|
|
|
2469
2496
|
# Manually trigger a worker
|
|
2470
|
-
npx
|
|
2497
|
+
npx ruflo@v3alpha daemon trigger map
|
|
2471
2498
|
|
|
2472
2499
|
# Enable/disable workers
|
|
2473
|
-
npx
|
|
2500
|
+
npx ruflo@v3alpha daemon enable map audit optimize
|
|
2474
2501
|
|
|
2475
2502
|
# Stop daemon
|
|
2476
|
-
npx
|
|
2503
|
+
npx ruflo@v3alpha daemon stop
|
|
2477
2504
|
```
|
|
2478
2505
|
|
|
2479
2506
|
**Daemon Status Output:**
|
|
@@ -2547,7 +2574,7 @@ Shell-based daemons for monitoring (Linux/macOS only):
|
|
|
2547
2574
|
<details>
|
|
2548
2575
|
<summary>โจ๏ธ <strong>V3 CLI Commands</strong> โ 26 commands with 140+ subcommands</summary>
|
|
2549
2576
|
|
|
2550
|
-
Complete command-line interface for all
|
|
2577
|
+
Complete command-line interface for all Ruflo operations.
|
|
2551
2578
|
|
|
2552
2579
|
**Core Commands:**
|
|
2553
2580
|
|
|
@@ -2589,25 +2616,25 @@ Complete command-line interface for all Claude-Flow operations.
|
|
|
2589
2616
|
|
|
2590
2617
|
```bash
|
|
2591
2618
|
# Initialize project with wizard
|
|
2592
|
-
npx
|
|
2619
|
+
npx ruflo@v3alpha init --wizard
|
|
2593
2620
|
|
|
2594
2621
|
# Start daemon with background workers
|
|
2595
|
-
npx
|
|
2622
|
+
npx ruflo@v3alpha daemon start
|
|
2596
2623
|
|
|
2597
2624
|
# Spawn an agent with specific type
|
|
2598
|
-
npx
|
|
2625
|
+
npx ruflo@v3alpha agent spawn -t coder --name my-coder
|
|
2599
2626
|
|
|
2600
2627
|
# Initialize swarm with V3 mode
|
|
2601
|
-
npx
|
|
2628
|
+
npx ruflo@v3alpha swarm init --v3-mode
|
|
2602
2629
|
|
|
2603
2630
|
# Search memory (HNSW-indexed, 150x faster)
|
|
2604
|
-
npx
|
|
2631
|
+
npx ruflo@v3alpha memory search -q "authentication patterns"
|
|
2605
2632
|
|
|
2606
2633
|
# Run security scan
|
|
2607
|
-
npx
|
|
2634
|
+
npx ruflo@v3alpha security scan --depth full
|
|
2608
2635
|
|
|
2609
2636
|
# Performance benchmark
|
|
2610
|
-
npx
|
|
2637
|
+
npx ruflo@v3alpha performance benchmark --suite all
|
|
2611
2638
|
```
|
|
2612
2639
|
|
|
2613
2640
|
</details>
|
|
@@ -2615,7 +2642,7 @@ npx claude-flow@v3alpha performance benchmark --suite all
|
|
|
2615
2642
|
<details>
|
|
2616
2643
|
<summary>๐ฉบ <strong>Doctor Health Checks</strong> โ System diagnostics with auto-fix</summary>
|
|
2617
2644
|
|
|
2618
|
-
Run `npx
|
|
2645
|
+
Run `npx ruflo@v3alpha doctor` to diagnose and fix common issues.
|
|
2619
2646
|
|
|
2620
2647
|
**Health Checks Performed:**
|
|
2621
2648
|
|
|
@@ -2636,22 +2663,22 @@ Run `npx claude-flow@v3alpha doctor` to diagnose and fix common issues.
|
|
|
2636
2663
|
|
|
2637
2664
|
```bash
|
|
2638
2665
|
# Run full diagnostics
|
|
2639
|
-
npx
|
|
2666
|
+
npx ruflo@v3alpha doctor
|
|
2640
2667
|
|
|
2641
2668
|
# Run diagnostics with auto-fix
|
|
2642
|
-
npx
|
|
2669
|
+
npx ruflo@v3alpha doctor --fix
|
|
2643
2670
|
|
|
2644
2671
|
# Check specific component
|
|
2645
|
-
npx
|
|
2672
|
+
npx ruflo@v3alpha doctor --component memory
|
|
2646
2673
|
|
|
2647
2674
|
# Verbose output
|
|
2648
|
-
npx
|
|
2675
|
+
npx ruflo@v3alpha doctor --verbose
|
|
2649
2676
|
```
|
|
2650
2677
|
|
|
2651
2678
|
**Output Example:**
|
|
2652
2679
|
|
|
2653
2680
|
```
|
|
2654
|
-
๐ฉบ
|
|
2681
|
+
๐ฉบ Ruflo Doctor v3.0.0-alpha
|
|
2655
2682
|
|
|
2656
2683
|
โ
Node.js 20.11.0 (required: 20+)
|
|
2657
2684
|
โ
npm 10.2.4 (required: 9+)
|
|
@@ -2695,16 +2722,16 @@ The embeddings package (v3.0.0-alpha.12) provides high-performance vector embedd
|
|
|
2695
2722
|
|
|
2696
2723
|
```bash
|
|
2697
2724
|
# Initialize embeddings system
|
|
2698
|
-
npx
|
|
2725
|
+
npx ruflo@v3alpha embeddings init
|
|
2699
2726
|
|
|
2700
2727
|
# Generate embedding for text
|
|
2701
|
-
npx
|
|
2728
|
+
npx ruflo@v3alpha embeddings embed "authentication patterns"
|
|
2702
2729
|
|
|
2703
2730
|
# Batch embed multiple texts
|
|
2704
|
-
npx
|
|
2731
|
+
npx ruflo@v3alpha embeddings batch --file texts.txt
|
|
2705
2732
|
|
|
2706
2733
|
# Search with semantic similarity
|
|
2707
|
-
npx
|
|
2734
|
+
npx ruflo@v3alpha embeddings search "login flow" --top-k 5
|
|
2708
2735
|
```
|
|
2709
2736
|
|
|
2710
2737
|
**Programmatic:**
|
|
@@ -2741,59 +2768,59 @@ Real-world scenarios and pre-built workflows for common tasks.
|
|
|
2741
2768
|
|
|
2742
2769
|
| Scenario | What It Solves | How To Do It |
|
|
2743
2770
|
|----------|----------------|--------------|
|
|
2744
|
-
| **Code Review** | Get thorough reviews with security, performance, and style checks | `npx
|
|
2745
|
-
| **Test Generation** | Auto-generate unit, integration, and e2e tests for existing code | `npx
|
|
2746
|
-
| **Refactoring** | Safely restructure code while maintaining behavior | `npx
|
|
2747
|
-
| **Bug Fixing** | Diagnose and fix bugs with full context analysis | `npx
|
|
2771
|
+
| **Code Review** | Get thorough reviews with security, performance, and style checks | `npx ruflo@v3alpha --agent reviewer --task "Review PR #123"` |
|
|
2772
|
+
| **Test Generation** | Auto-generate unit, integration, and e2e tests for existing code | `npx ruflo@v3alpha --agent tester --task "Write tests for auth module"` |
|
|
2773
|
+
| **Refactoring** | Safely restructure code while maintaining behavior | `npx ruflo@v3alpha --agent coder --task "Refactor user service to use repository pattern"` |
|
|
2774
|
+
| **Bug Fixing** | Diagnose and fix bugs with full context analysis | `npx ruflo@v3alpha --agent coder --task "Fix race condition in checkout flow"` |
|
|
2748
2775
|
|
|
2749
2776
|
### ๐ Security & Compliance
|
|
2750
2777
|
|
|
2751
2778
|
| Scenario | What It Solves | How To Do It |
|
|
2752
2779
|
|----------|----------------|--------------|
|
|
2753
|
-
| **Security Audit** | Find vulnerabilities before attackers do | `npx
|
|
2754
|
-
| **Dependency Scan** | Identify vulnerable packages and suggest upgrades | `npx
|
|
2755
|
-
| **Compliance Check** | Ensure code meets security standards | `npx
|
|
2780
|
+
| **Security Audit** | Find vulnerabilities before attackers do | `npx ruflo@v3alpha --agent security-architect --task "Audit for OWASP Top 10"` |
|
|
2781
|
+
| **Dependency Scan** | Identify vulnerable packages and suggest upgrades | `npx ruflo@v3alpha security scan --depth full` |
|
|
2782
|
+
| **Compliance Check** | Ensure code meets security standards | `npx ruflo@v3alpha --agent security-architect --task "Check PCI-DSS compliance"` |
|
|
2756
2783
|
|
|
2757
2784
|
### ๐ Multi-Agent Swarms
|
|
2758
2785
|
|
|
2759
2786
|
| Scenario | What It Solves | How To Do It |
|
|
2760
2787
|
|----------|----------------|--------------|
|
|
2761
|
-
| **Feature Development** | Coordinate multiple agents on complex features | `npx
|
|
2762
|
-
| **Large Refactors** | Parallel refactoring across many files without conflicts | `npx
|
|
2763
|
-
| **Codebase Migration** | Migrate frameworks, languages, or patterns systematically | `npx
|
|
2788
|
+
| **Feature Development** | Coordinate multiple agents on complex features | `npx ruflo@v3alpha swarm init --topology hierarchical && npx ruflo@v3alpha task orchestrate "Build user dashboard"` |
|
|
2789
|
+
| **Large Refactors** | Parallel refactoring across many files without conflicts | `npx ruflo@v3alpha swarm init --topology mesh --max-agents 8` |
|
|
2790
|
+
| **Codebase Migration** | Migrate frameworks, languages, or patterns systematically | `npx ruflo@v3alpha task orchestrate "Migrate from Express to Fastify" --strategy adaptive` |
|
|
2764
2791
|
|
|
2765
2792
|
### ๐ Performance & Optimization
|
|
2766
2793
|
|
|
2767
2794
|
| Scenario | What It Solves | How To Do It |
|
|
2768
2795
|
|----------|----------------|--------------|
|
|
2769
|
-
| **Performance Profiling** | Find and fix bottlenecks in your application | `npx
|
|
2770
|
-
| **Query Optimization** | Speed up slow database queries | `npx
|
|
2771
|
-
| **Memory Analysis** | Reduce memory usage and fix leaks | `npx
|
|
2796
|
+
| **Performance Profiling** | Find and fix bottlenecks in your application | `npx ruflo@v3alpha --agent perf-analyzer --task "Profile API endpoints"` |
|
|
2797
|
+
| **Query Optimization** | Speed up slow database queries | `npx ruflo@v3alpha hooks route "Optimize database queries"` |
|
|
2798
|
+
| **Memory Analysis** | Reduce memory usage and fix leaks | `npx ruflo@v3alpha --agent perf-analyzer --task "Analyze memory usage patterns"` |
|
|
2772
2799
|
|
|
2773
2800
|
### ๐ GitHub & DevOps
|
|
2774
2801
|
|
|
2775
2802
|
| Scenario | What It Solves | How To Do It |
|
|
2776
2803
|
|----------|----------------|--------------|
|
|
2777
|
-
| **PR Management** | Review, approve, and merge PRs efficiently | `npx
|
|
2778
|
-
| **Issue Triage** | Categorize, prioritize, and assign issues automatically | `npx
|
|
2779
|
-
| **Release Management** | Coordinate releases with changelogs and versioning | `npx
|
|
2780
|
-
| **CI/CD Optimization** | Speed up pipelines and reduce flaky tests | `npx
|
|
2804
|
+
| **PR Management** | Review, approve, and merge PRs efficiently | `npx ruflo@v3alpha --agent pr-manager --task "Review open PRs"` |
|
|
2805
|
+
| **Issue Triage** | Categorize, prioritize, and assign issues automatically | `npx ruflo@v3alpha --agent issue-tracker --task "Triage new issues"` |
|
|
2806
|
+
| **Release Management** | Coordinate releases with changelogs and versioning | `npx ruflo@v3alpha --agent release-manager --task "Prepare v2.0 release"` |
|
|
2807
|
+
| **CI/CD Optimization** | Speed up pipelines and reduce flaky tests | `npx ruflo@v3alpha --agent cicd-engineer --task "Optimize GitHub Actions workflow"` |
|
|
2781
2808
|
|
|
2782
2809
|
### ๐ Spec-Driven Development
|
|
2783
2810
|
|
|
2784
2811
|
| Scenario | What It Solves | How To Do It |
|
|
2785
2812
|
|----------|----------------|--------------|
|
|
2786
|
-
| **Generate Specs** | Create complete specifications before coding | `npx
|
|
2787
|
-
| **Validate Implementation** | Ensure code matches specifications | `npx
|
|
2788
|
-
| **Track Compliance** | Monitor spec adherence across the team | `npx
|
|
2813
|
+
| **Generate Specs** | Create complete specifications before coding | `npx ruflo@v3alpha --agent architect --task "Create ADR for authentication system"` |
|
|
2814
|
+
| **Validate Implementation** | Ensure code matches specifications | `npx ruflo@v3alpha hooks progress --detailed` |
|
|
2815
|
+
| **Track Compliance** | Monitor spec adherence across the team | `npx ruflo@v3alpha progress sync` |
|
|
2789
2816
|
|
|
2790
2817
|
### ๐ง Learning & Intelligence
|
|
2791
2818
|
|
|
2792
2819
|
| Scenario | What It Solves | How To Do It |
|
|
2793
2820
|
|----------|----------------|--------------|
|
|
2794
|
-
| **Bootstrap Intelligence** | Train the system on your codebase patterns | `npx
|
|
2795
|
-
| **Optimize Routing** | Improve task-to-agent matching over time | `npx
|
|
2796
|
-
| **Transfer Learning** | Apply patterns learned from other projects | `npx
|
|
2821
|
+
| **Bootstrap Intelligence** | Train the system on your codebase patterns | `npx ruflo@v3alpha hooks pretrain --depth deep` |
|
|
2822
|
+
| **Optimize Routing** | Improve task-to-agent matching over time | `npx ruflo@v3alpha hooks route "<task>" --include-explanation` |
|
|
2823
|
+
| **Transfer Learning** | Apply patterns learned from other projects | `npx ruflo@v3alpha hooks transfer <sourceProject>` |
|
|
2797
2824
|
|
|
2798
2825
|
</details>
|
|
2799
2826
|
|
|
@@ -2851,7 +2878,7 @@ When hooks run, they emit signals that guide routing decisions. Watch for these
|
|
|
2851
2878
|
|
|
2852
2879
|
**Example Hook Output:**
|
|
2853
2880
|
```bash
|
|
2854
|
-
$ npx
|
|
2881
|
+
$ npx ruflo@v3alpha hooks pre-task --description "convert var to const in utils.ts"
|
|
2855
2882
|
|
|
2856
2883
|
[AGENT_BOOSTER_AVAILABLE] Intent: var-to-const
|
|
2857
2884
|
Recommendation: Use Edit tool directly
|
|
@@ -2874,8 +2901,8 @@ Cost: $0
|
|
|
2874
2901
|
|
|
2875
2902
|
```bash
|
|
2876
2903
|
# Example: Edit with pattern learning
|
|
2877
|
-
npx
|
|
2878
|
-
npx
|
|
2904
|
+
npx ruflo@v3alpha hooks pre-edit ./src/auth.ts
|
|
2905
|
+
npx ruflo@v3alpha hooks post-edit ./src/auth.ts --success true --train-patterns
|
|
2879
2906
|
```
|
|
2880
2907
|
|
|
2881
2908
|
#### ๐ง Intelligence & Routing Hooks (8 hooks)
|
|
@@ -2893,10 +2920,10 @@ npx claude-flow@v3alpha hooks post-edit ./src/auth.ts --success true --train-pat
|
|
|
2893
2920
|
|
|
2894
2921
|
```bash
|
|
2895
2922
|
# Route a task with explanation
|
|
2896
|
-
npx
|
|
2923
|
+
npx ruflo@v3alpha hooks route "refactor authentication to use JWT" --include-explanation
|
|
2897
2924
|
|
|
2898
2925
|
# Bootstrap intelligence from your codebase
|
|
2899
|
-
npx
|
|
2926
|
+
npx ruflo@v3alpha hooks pretrain --depth deep --model-type moe
|
|
2900
2927
|
```
|
|
2901
2928
|
|
|
2902
2929
|
#### ๐
Session Management Hooks (4 hooks)
|
|
@@ -2910,10 +2937,10 @@ npx claude-flow@v3alpha hooks pretrain --depth deep --model-type moe
|
|
|
2910
2937
|
|
|
2911
2938
|
```bash
|
|
2912
2939
|
# Start session with auto-daemon
|
|
2913
|
-
npx
|
|
2940
|
+
npx ruflo@v3alpha hooks session-start --session-id "feature-auth" --start-daemon
|
|
2914
2941
|
|
|
2915
2942
|
# End session and export learnings
|
|
2916
|
-
npx
|
|
2943
|
+
npx ruflo@v3alpha hooks session-end --export-metrics --persist-patterns
|
|
2917
2944
|
```
|
|
2918
2945
|
|
|
2919
2946
|
#### ๐ค Intelligence System Hooks (9 hooks)
|
|
@@ -2932,13 +2959,13 @@ npx claude-flow@v3alpha hooks session-end --export-metrics --persist-patterns
|
|
|
2932
2959
|
|
|
2933
2960
|
```bash
|
|
2934
2961
|
# Start trajectory for complex task
|
|
2935
|
-
npx
|
|
2962
|
+
npx ruflo@v3alpha hooks intelligence trajectory-start --task "implement OAuth2"
|
|
2936
2963
|
|
|
2937
2964
|
# Record successful action
|
|
2938
|
-
npx
|
|
2965
|
+
npx ruflo@v3alpha hooks intelligence trajectory-step --action "created token service" --quality 0.9
|
|
2939
2966
|
|
|
2940
2967
|
# End trajectory and trigger learning
|
|
2941
|
-
npx
|
|
2968
|
+
npx ruflo@v3alpha hooks intelligence trajectory-end --success true
|
|
2942
2969
|
```
|
|
2943
2970
|
|
|
2944
2971
|
### 12 Background Workers (Auto-Triggered)
|
|
@@ -2962,13 +2989,13 @@ Workers run automatically based on context, or dispatch manually.
|
|
|
2962
2989
|
|
|
2963
2990
|
```bash
|
|
2964
2991
|
# List all workers
|
|
2965
|
-
npx
|
|
2992
|
+
npx ruflo@v3alpha hooks worker list
|
|
2966
2993
|
|
|
2967
2994
|
# Manually dispatch security audit
|
|
2968
|
-
npx
|
|
2995
|
+
npx ruflo@v3alpha hooks worker dispatch --trigger audit --context "./src/auth"
|
|
2969
2996
|
|
|
2970
2997
|
# Check worker status
|
|
2971
|
-
npx
|
|
2998
|
+
npx ruflo@v3alpha hooks worker status
|
|
2972
2999
|
```
|
|
2973
3000
|
|
|
2974
3001
|
### Model Routing Hooks (3 hooks)
|
|
@@ -2983,10 +3010,10 @@ Automatically selects haiku/sonnet/opus based on task complexity.
|
|
|
2983
3010
|
|
|
2984
3011
|
```bash
|
|
2985
3012
|
# Get model recommendation
|
|
2986
|
-
npx
|
|
3013
|
+
npx ruflo@v3alpha hooks model-route --task "fix typo in README"
|
|
2987
3014
|
# โ Recommends: haiku (simple task, low complexity)
|
|
2988
3015
|
|
|
2989
|
-
npx
|
|
3016
|
+
npx ruflo@v3alpha hooks model-route --task "design distributed consensus system"
|
|
2990
3017
|
# โ Recommends: opus (complex architecture, high reasoning)
|
|
2991
3018
|
```
|
|
2992
3019
|
|
|
@@ -3007,21 +3034,21 @@ npx claude-flow@v3alpha hooks model-route --task "design distributed consensus s
|
|
|
3007
3034
|
# โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
|
|
3008
3035
|
|
|
3009
3036
|
# Route task to best agent
|
|
3010
|
-
npx
|
|
3037
|
+
npx ruflo@v3alpha hooks route "<task>" --include-explanation
|
|
3011
3038
|
|
|
3012
3039
|
# Start/end session with learning
|
|
3013
|
-
npx
|
|
3014
|
-
npx
|
|
3040
|
+
npx ruflo@v3alpha hooks session-start --start-daemon
|
|
3041
|
+
npx ruflo@v3alpha hooks session-end --persist-patterns
|
|
3015
3042
|
|
|
3016
3043
|
# View what the system has learned
|
|
3017
|
-
npx
|
|
3018
|
-
npx
|
|
3044
|
+
npx ruflo@v3alpha hooks metrics
|
|
3045
|
+
npx ruflo@v3alpha hooks intelligence stats
|
|
3019
3046
|
|
|
3020
3047
|
# Bootstrap on new project
|
|
3021
|
-
npx
|
|
3048
|
+
npx ruflo@v3alpha hooks pretrain --depth deep
|
|
3022
3049
|
|
|
3023
3050
|
# Dispatch background worker
|
|
3024
|
-
npx
|
|
3051
|
+
npx ruflo@v3alpha hooks worker dispatch --trigger audit
|
|
3025
3052
|
```
|
|
3026
3053
|
|
|
3027
3054
|
</details>
|
|
@@ -3047,38 +3074,38 @@ Share learned patterns across projects, teams, and the community via the decentr
|
|
|
3047
3074
|
|
|
3048
3075
|
```bash
|
|
3049
3076
|
# Export learned patterns to file
|
|
3050
|
-
npx
|
|
3077
|
+
npx ruflo@v3alpha memory export --format json --output ./patterns.json
|
|
3051
3078
|
|
|
3052
3079
|
# Export specific namespace
|
|
3053
|
-
npx
|
|
3080
|
+
npx ruflo@v3alpha memory export --namespace "security" --output ./security-patterns.json
|
|
3054
3081
|
|
|
3055
3082
|
# Export with embeddings (larger file, faster import)
|
|
3056
|
-
npx
|
|
3083
|
+
npx ruflo@v3alpha memory export --include-embeddings --output ./full-export.json
|
|
3057
3084
|
|
|
3058
3085
|
# Export agent configurations
|
|
3059
|
-
npx
|
|
3086
|
+
npx ruflo@v3alpha config export --scope project --output ./agent-configs.json
|
|
3060
3087
|
|
|
3061
3088
|
# Export session state
|
|
3062
|
-
npx
|
|
3089
|
+
npx ruflo@v3alpha session export --session-id "my-session" --output ./session.json
|
|
3063
3090
|
```
|
|
3064
3091
|
|
|
3065
3092
|
### Import Commands
|
|
3066
3093
|
|
|
3067
3094
|
```bash
|
|
3068
3095
|
# Import patterns from file
|
|
3069
|
-
npx
|
|
3096
|
+
npx ruflo@v3alpha memory import --input ./patterns.json
|
|
3070
3097
|
|
|
3071
3098
|
# Import and merge with existing (don't overwrite)
|
|
3072
|
-
npx
|
|
3099
|
+
npx ruflo@v3alpha memory import --input ./patterns.json --merge
|
|
3073
3100
|
|
|
3074
3101
|
# Import from another project
|
|
3075
|
-
npx
|
|
3102
|
+
npx ruflo@v3alpha hooks transfer --source-path ../other-project
|
|
3076
3103
|
|
|
3077
3104
|
# Import agent configurations
|
|
3078
|
-
npx
|
|
3105
|
+
npx ruflo@v3alpha config import --input ./agent-configs.json --scope project
|
|
3079
3106
|
|
|
3080
3107
|
# Restore session
|
|
3081
|
-
npx
|
|
3108
|
+
npx ruflo@v3alpha session restore --session-id "my-session"
|
|
3082
3109
|
```
|
|
3083
3110
|
|
|
3084
3111
|
### Pattern Store (IPFS Marketplace)
|
|
@@ -3096,13 +3123,13 @@ Decentralized pattern marketplace for sharing and discovering community patterns
|
|
|
3096
3123
|
|
|
3097
3124
|
```bash
|
|
3098
3125
|
# Search for authentication patterns
|
|
3099
|
-
npx
|
|
3126
|
+
npx ruflo@v3alpha transfer-store search --query "authentication" --min-rating 4.0
|
|
3100
3127
|
|
|
3101
3128
|
# Download a pattern
|
|
3102
|
-
npx
|
|
3129
|
+
npx ruflo@v3alpha transfer-store download --id "auth-jwt-patterns-v2" --verify
|
|
3103
3130
|
|
|
3104
3131
|
# Publish your patterns
|
|
3105
|
-
npx
|
|
3132
|
+
npx ruflo@v3alpha transfer-store publish --input ./my-patterns.json --category "security"
|
|
3106
3133
|
```
|
|
3107
3134
|
|
|
3108
3135
|
### Plugin Store
|
|
@@ -3120,22 +3147,22 @@ Discover and install community plugins from the **live IPFS registry** with 19 o
|
|
|
3120
3147
|
|
|
3121
3148
|
```bash
|
|
3122
3149
|
# List plugins with live ratings from Cloud Function
|
|
3123
|
-
npx
|
|
3150
|
+
npx ruflo@v3alpha plugins list
|
|
3124
3151
|
|
|
3125
3152
|
# Filter by type
|
|
3126
|
-
npx
|
|
3153
|
+
npx ruflo@v3alpha plugins list --type integration
|
|
3127
3154
|
|
|
3128
3155
|
# Rate a plugin
|
|
3129
|
-
npx
|
|
3156
|
+
npx ruflo@v3alpha plugins rate --name @claude-flow/embeddings --rating 5
|
|
3130
3157
|
|
|
3131
3158
|
# Search for MCP tool plugins
|
|
3132
|
-
npx
|
|
3159
|
+
npx ruflo@v3alpha transfer plugin-search --type "mcp-tool" --verified
|
|
3133
3160
|
|
|
3134
3161
|
# Get plugin info
|
|
3135
|
-
npx
|
|
3162
|
+
npx ruflo@v3alpha transfer plugin-info --name "semantic-code-search"
|
|
3136
3163
|
|
|
3137
3164
|
# List official plugins
|
|
3138
|
-
npx
|
|
3165
|
+
npx ruflo@v3alpha transfer plugin-official
|
|
3139
3166
|
```
|
|
3140
3167
|
|
|
3141
3168
|
#### Live IPFS Plugin Registry
|
|
@@ -3168,10 +3195,10 @@ Patterns and models are distributed via IPFS for decentralization and integrity.
|
|
|
3168
3195
|
|
|
3169
3196
|
```bash
|
|
3170
3197
|
# Resolve IPNS name to CID
|
|
3171
|
-
npx
|
|
3198
|
+
npx ruflo@v3alpha transfer ipfs-resolve --name "/ipns/patterns.ruflo.io"
|
|
3172
3199
|
|
|
3173
3200
|
# Detect PII before publishing
|
|
3174
|
-
npx
|
|
3201
|
+
npx ruflo@v3alpha transfer detect-pii --content "$(cat ./patterns.json)"
|
|
3175
3202
|
```
|
|
3176
3203
|
|
|
3177
3204
|
### Model & Learning Pattern Import/Export
|
|
@@ -3194,7 +3221,7 @@ curl -X POST "https://api.pinata.cloud/pinning/pinJSONToIPFS" \
|
|
|
3194
3221
|
"name": "my-patterns",
|
|
3195
3222
|
"patterns": [...]
|
|
3196
3223
|
},
|
|
3197
|
-
"pinataMetadata": {"name": "
|
|
3224
|
+
"pinataMetadata": {"name": "ruflo-learning-pattern"}
|
|
3198
3225
|
}'
|
|
3199
3226
|
|
|
3200
3227
|
# Import a pattern from IPFS CID
|
|
@@ -3236,13 +3263,13 @@ Import pre-trained learning patterns for common tasks. **90.5% average accuracy*
|
|
|
3236
3263
|
curl -s "https://gateway.pinata.cloud/ipfs/QmNr1yYMKi7YBaL8JSztQyuB5ZUaTdRMLxJC1pBpGbjsTc" | jq '.models[].name'
|
|
3237
3264
|
|
|
3238
3265
|
# Import all models
|
|
3239
|
-
npx
|
|
3266
|
+
npx ruflo@v3alpha transfer import --cid QmNr1yYMKi7YBaL8JSztQyuB5ZUaTdRMLxJC1pBpGbjsTc
|
|
3240
3267
|
|
|
3241
3268
|
# Import specific category
|
|
3242
|
-
npx
|
|
3269
|
+
npx ruflo@v3alpha neural import --model security-review-patterns --source ipfs
|
|
3243
3270
|
|
|
3244
3271
|
# Use patterns in routing
|
|
3245
|
-
npx
|
|
3272
|
+
npx ruflo@v3alpha hooks route --task "review authentication code" --use-patterns
|
|
3246
3273
|
```
|
|
3247
3274
|
|
|
3248
3275
|
#### Benefits vs Fresh Install
|
|
@@ -3267,7 +3294,7 @@ npx claude-flow@v3alpha hooks route --task "review authentication code" --use-pa
|
|
|
3267
3294
|
|
|
3268
3295
|
```bash
|
|
3269
3296
|
# Install a pattern pack
|
|
3270
|
-
npx
|
|
3297
|
+
npx ruflo@v3alpha transfer-store download --id "security-essentials" --apply
|
|
3271
3298
|
```
|
|
3272
3299
|
|
|
3273
3300
|
### RuVector WASM Neural Training
|
|
@@ -3285,25 +3312,25 @@ Real WASM-accelerated neural training using `@ruvector/learning-wasm` and `@ruve
|
|
|
3285
3312
|
|
|
3286
3313
|
```bash
|
|
3287
3314
|
# List available pre-trained models from IPFS registry
|
|
3288
|
-
npx
|
|
3315
|
+
npx ruflo@v3alpha neural list
|
|
3289
3316
|
|
|
3290
3317
|
# List models by category
|
|
3291
|
-
npx
|
|
3318
|
+
npx ruflo@v3alpha neural list --category security
|
|
3292
3319
|
|
|
3293
3320
|
# Train with WASM acceleration
|
|
3294
|
-
npx
|
|
3321
|
+
npx ruflo@v3alpha neural train -p coordination -e 100 --wasm --flash --contrastive
|
|
3295
3322
|
|
|
3296
3323
|
# Train security patterns
|
|
3297
|
-
npx
|
|
3324
|
+
npx ruflo@v3alpha neural train -p security --wasm --contrastive
|
|
3298
3325
|
|
|
3299
3326
|
# Benchmark WASM performance
|
|
3300
|
-
npx
|
|
3327
|
+
npx ruflo@v3alpha neural benchmark -d 256 -i 1000
|
|
3301
3328
|
|
|
3302
3329
|
# Import pre-trained models
|
|
3303
|
-
npx
|
|
3330
|
+
npx ruflo@v3alpha neural import --cid QmNr1yYMKi7YBaL8JSztQyuB5ZUaTdRMLxJC1pBpGbjsTc
|
|
3304
3331
|
|
|
3305
3332
|
# Export trained patterns to IPFS
|
|
3306
|
-
npx
|
|
3333
|
+
npx ruflo@v3alpha neural export --ipfs --sign
|
|
3307
3334
|
```
|
|
3308
3335
|
|
|
3309
3336
|
#### Benchmark Results
|
|
@@ -3642,9 +3669,9 @@ Skills are **reusable workflows** that combine agents, hooks, and patterns into
|
|
|
3642
3669
|
/v3-security-overhaul
|
|
3643
3670
|
|
|
3644
3671
|
# Via CLI
|
|
3645
|
-
npx
|
|
3646
|
-
npx
|
|
3647
|
-
npx
|
|
3672
|
+
npx ruflo@v3alpha skill run github-code-review
|
|
3673
|
+
npx ruflo@v3alpha skill list
|
|
3674
|
+
npx ruflo@v3alpha skill info sparc-methodology
|
|
3648
3675
|
```
|
|
3649
3676
|
|
|
3650
3677
|
### Creating Custom Skills
|
|
@@ -3701,21 +3728,21 @@ The Claims system manages **who is working on what** โ whether human or agent.
|
|
|
3701
3728
|
|
|
3702
3729
|
| Command | What It Does | Example |
|
|
3703
3730
|
|---------|--------------|---------|
|
|
3704
|
-
| `issues list` | See all issues and their status | `npx
|
|
3705
|
-
| `issues claim` | Claim an issue for yourself/agent | `npx
|
|
3706
|
-
| `issues release` | Release your claim | `npx
|
|
3707
|
-
| `issues handoff` | Hand off to another worker | `npx
|
|
3708
|
-
| `issues status` | Update progress on claimed work | `npx
|
|
3709
|
-
| `issues stealable` | List abandoned/stuck issues | `npx
|
|
3710
|
-
| `issues steal` | Take over stealable issue | `npx
|
|
3711
|
-
| `issues load` | View agent workloads | `npx
|
|
3712
|
-
| `issues rebalance` | Redistribute work evenly | `npx
|
|
3713
|
-
| `issues board` | Visual board view | `npx
|
|
3731
|
+
| `issues list` | See all issues and their status | `npx ruflo@v3alpha issues list` |
|
|
3732
|
+
| `issues claim` | Claim an issue for yourself/agent | `npx ruflo@v3alpha issues claim #123 --as coder-1` |
|
|
3733
|
+
| `issues release` | Release your claim | `npx ruflo@v3alpha issues release #123` |
|
|
3734
|
+
| `issues handoff` | Hand off to another worker | `npx ruflo@v3alpha issues handoff #123 --to reviewer` |
|
|
3735
|
+
| `issues status` | Update progress on claimed work | `npx ruflo@v3alpha issues status #123 --progress 75` |
|
|
3736
|
+
| `issues stealable` | List abandoned/stuck issues | `npx ruflo@v3alpha issues stealable` |
|
|
3737
|
+
| `issues steal` | Take over stealable issue | `npx ruflo@v3alpha issues steal #123` |
|
|
3738
|
+
| `issues load` | View agent workloads | `npx ruflo@v3alpha issues load` |
|
|
3739
|
+
| `issues rebalance` | Redistribute work evenly | `npx ruflo@v3alpha issues rebalance --dry-run` |
|
|
3740
|
+
| `issues board` | Visual board view | `npx ruflo@v3alpha issues board` |
|
|
3714
3741
|
|
|
3715
3742
|
### Visual Board View
|
|
3716
3743
|
|
|
3717
3744
|
```bash
|
|
3718
|
-
npx
|
|
3745
|
+
npx ruflo@v3alpha issues board
|
|
3719
3746
|
```
|
|
3720
3747
|
|
|
3721
3748
|
```
|
|
@@ -3737,13 +3764,13 @@ When you need to pass work to someone else:
|
|
|
3737
3764
|
|
|
3738
3765
|
```bash
|
|
3739
3766
|
# 1. Request handoff with context
|
|
3740
|
-
npx
|
|
3767
|
+
npx ruflo@v3alpha issues handoff #123 \
|
|
3741
3768
|
--to security-architect \
|
|
3742
3769
|
--reason "Needs security review" \
|
|
3743
3770
|
--progress 80
|
|
3744
3771
|
|
|
3745
3772
|
# 2. Target accepts handoff
|
|
3746
|
-
npx
|
|
3773
|
+
npx ruflo@v3alpha issues accept #123 --as security-architect
|
|
3747
3774
|
|
|
3748
3775
|
# 3. Work continues with full context
|
|
3749
3776
|
```
|
|
@@ -3752,7 +3779,7 @@ npx claude-flow@v3alpha issues accept #123 --as security-architect
|
|
|
3752
3779
|
|
|
3753
3780
|
```bash
|
|
3754
3781
|
# View current load
|
|
3755
|
-
npx
|
|
3782
|
+
npx ruflo@v3alpha issues load
|
|
3756
3783
|
|
|
3757
3784
|
# Output:
|
|
3758
3785
|
# Agent | Claims | Load | Status
|
|
@@ -3763,7 +3790,7 @@ npx claude-flow@v3alpha issues load
|
|
|
3763
3790
|
# security-arch | 0 | 0% | ๐ข Available
|
|
3764
3791
|
|
|
3765
3792
|
# Auto-rebalance
|
|
3766
|
-
npx
|
|
3793
|
+
npx ruflo@v3alpha issues rebalance
|
|
3767
3794
|
```
|
|
3768
3795
|
|
|
3769
3796
|
### MCP Tools
|
|
@@ -3824,14 +3851,14 @@ The Route system uses **Q-Learning** to automatically assign tasks to the best a
|
|
|
3824
3851
|
|
|
3825
3852
|
| Command | What It Does | Example |
|
|
3826
3853
|
|---------|--------------|---------|
|
|
3827
|
-
| `route task` | Get agent recommendation | `npx
|
|
3828
|
-
| `route explain` | Understand routing decision | `npx
|
|
3829
|
-
| `route coverage` | Route based on test coverage | `npx
|
|
3854
|
+
| `route task` | Get agent recommendation | `npx ruflo@v3alpha route task "implement OAuth2"` |
|
|
3855
|
+
| `route explain` | Understand routing decision | `npx ruflo@v3alpha route explain "task"` |
|
|
3856
|
+
| `route coverage` | Route based on test coverage | `npx ruflo@v3alpha route coverage` |
|
|
3830
3857
|
|
|
3831
3858
|
### Example: Route a Task
|
|
3832
3859
|
|
|
3833
3860
|
```bash
|
|
3834
|
-
npx
|
|
3861
|
+
npx ruflo@v3alpha route task "refactor authentication to use JWT"
|
|
3835
3862
|
|
|
3836
3863
|
# Output:
|
|
3837
3864
|
# โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
|
|
@@ -3858,7 +3885,7 @@ npx claude-flow@v3alpha route task "refactor authentication to use JWT"
|
|
|
3858
3885
|
Routes tasks to agents based on **test coverage gaps**:
|
|
3859
3886
|
|
|
3860
3887
|
```bash
|
|
3861
|
-
npx
|
|
3888
|
+
npx ruflo@v3alpha route coverage
|
|
3862
3889
|
|
|
3863
3890
|
# Finds untested code and routes to tester agent:
|
|
3864
3891
|
# โข src/auth/jwt.ts - 23% coverage โ tester
|
|
@@ -3870,10 +3897,10 @@ npx claude-flow@v3alpha route coverage
|
|
|
3870
3897
|
|
|
3871
3898
|
```bash
|
|
3872
3899
|
# Route via hooks (preferred)
|
|
3873
|
-
npx
|
|
3900
|
+
npx ruflo@v3alpha hooks route "implement caching layer" --include-explanation
|
|
3874
3901
|
|
|
3875
3902
|
# Record outcome for learning
|
|
3876
|
-
npx
|
|
3903
|
+
npx ruflo@v3alpha hooks post-task --task-id "task-123" --success true --agent coder
|
|
3877
3904
|
```
|
|
3878
3905
|
|
|
3879
3906
|
### How Q-Learning Improves Over Time
|
|
@@ -3893,12 +3920,12 @@ The system **remembers** what works and applies it to future similar tasks.
|
|
|
3893
3920
|
|
|
3894
3921
|
## ๐ป Programmatic Usage
|
|
3895
3922
|
|
|
3896
|
-
Use
|
|
3923
|
+
Use Ruflo packages directly in your applications.
|
|
3897
3924
|
|
|
3898
3925
|
<details>
|
|
3899
|
-
<summary>๐ป <strong>Programmatic SDK</strong> โ Use
|
|
3926
|
+
<summary>๐ป <strong>Programmatic SDK</strong> โ Use Ruflo in Your Code</summary>
|
|
3900
3927
|
|
|
3901
|
-
Use
|
|
3928
|
+
Use Ruflo packages directly in your TypeScript/JavaScript applications.
|
|
3902
3929
|
|
|
3903
3930
|
### Installation
|
|
3904
3931
|
|
|
@@ -3907,7 +3934,7 @@ Use Claude-Flow packages directly in your TypeScript/JavaScript applications.
|
|
|
3907
3934
|
npm install @claude-flow/cli @claude-flow/memory @claude-flow/swarm
|
|
3908
3935
|
|
|
3909
3936
|
# Or install everything
|
|
3910
|
-
npm install
|
|
3937
|
+
npm install ruflo@v3alpha
|
|
3911
3938
|
```
|
|
3912
3939
|
|
|
3913
3940
|
### Quick Examples
|
|
@@ -3944,21 +3971,21 @@ console.log(results);
|
|
|
3944
3971
|
**CLI Commands:**
|
|
3945
3972
|
```bash
|
|
3946
3973
|
# Initialize memory database
|
|
3947
|
-
npx
|
|
3974
|
+
npx ruflo@alpha memory init --force
|
|
3948
3975
|
|
|
3949
3976
|
# Store patterns
|
|
3950
|
-
npx
|
|
3951
|
-
npx
|
|
3977
|
+
npx ruflo@alpha memory store --key "pattern-auth" --value "JWT authentication with refresh tokens"
|
|
3978
|
+
npx ruflo@alpha memory store --key "pattern-cache" --value "Redis caching for API responses"
|
|
3952
3979
|
|
|
3953
3980
|
# Build HNSW index for 150x-12,500x faster search
|
|
3954
|
-
npx
|
|
3981
|
+
npx ruflo@alpha memory search --query "authentication" --build-hnsw
|
|
3955
3982
|
|
|
3956
3983
|
# Semantic search (uses HNSW if built)
|
|
3957
|
-
npx
|
|
3984
|
+
npx ruflo@alpha memory search --query "how to cache data" --limit 5
|
|
3958
3985
|
|
|
3959
3986
|
# List and manage entries
|
|
3960
|
-
npx
|
|
3961
|
-
npx
|
|
3987
|
+
npx ruflo@alpha memory list --namespace patterns
|
|
3988
|
+
npx ruflo@alpha memory stats
|
|
3962
3989
|
```
|
|
3963
3990
|
|
|
3964
3991
|
</details>
|
|
@@ -4192,35 +4219,35 @@ console.log(`Hit rate: ${(stats.hitRate * 100).toFixed(1)}%`);
|
|
|
4192
4219
|
|
|
4193
4220
|
```bash
|
|
4194
4221
|
# Generate embedding
|
|
4195
|
-
|
|
4222
|
+
ruflo embeddings embed "Your text here"
|
|
4196
4223
|
|
|
4197
4224
|
# Batch embed from file
|
|
4198
|
-
|
|
4225
|
+
ruflo embeddings batch documents.txt -o embeddings.json
|
|
4199
4226
|
|
|
4200
4227
|
# Similarity search
|
|
4201
|
-
|
|
4228
|
+
ruflo embeddings search "query" --index ./vectors
|
|
4202
4229
|
|
|
4203
4230
|
# Document chunking
|
|
4204
|
-
|
|
4231
|
+
ruflo embeddings chunk document.txt --strategy sentence --max-size 512
|
|
4205
4232
|
|
|
4206
4233
|
# Normalize embeddings
|
|
4207
|
-
|
|
4234
|
+
ruflo embeddings normalize embeddings.json --type l2 -o normalized.json
|
|
4208
4235
|
|
|
4209
4236
|
# Convert to hyperbolic
|
|
4210
|
-
|
|
4237
|
+
ruflo embeddings hyperbolic embeddings.json -o poincare.json
|
|
4211
4238
|
|
|
4212
4239
|
# Neural operations
|
|
4213
|
-
|
|
4214
|
-
|
|
4215
|
-
|
|
4240
|
+
ruflo embeddings neural drift --baseline "context" --input "check"
|
|
4241
|
+
ruflo embeddings neural store --id mem-1 --content "data"
|
|
4242
|
+
ruflo embeddings neural recall "query" --top-k 5
|
|
4216
4243
|
|
|
4217
4244
|
# Model management
|
|
4218
|
-
|
|
4219
|
-
|
|
4245
|
+
ruflo embeddings models list
|
|
4246
|
+
ruflo embeddings models download all-MiniLM-L6-v2
|
|
4220
4247
|
|
|
4221
4248
|
# Cache management
|
|
4222
|
-
|
|
4223
|
-
|
|
4249
|
+
ruflo embeddings cache stats
|
|
4250
|
+
ruflo embeddings cache clear --older-than 7d
|
|
4224
4251
|
```
|
|
4225
4252
|
|
|
4226
4253
|
### Available Models
|
|
@@ -4271,7 +4298,7 @@ await hooks.endTrajectory(trajectory, { success: true });
|
|
|
4271
4298
|
|
|
4272
4299
|
| Package | Purpose | Main Exports |
|
|
4273
4300
|
|---------|---------|--------------|
|
|
4274
|
-
| `@claude-flow/memory` | Vector storage, HNSW | `AgentDB`, `
|
|
4301
|
+
| `@claude-flow/memory` | Vector storage, HNSW, self-learning graph | `AgentDB`, `AutoMemoryBridge`, `LearningBridge`, `MemoryGraph` |
|
|
4275
4302
|
| `@claude-flow/swarm` | Agent coordination | `createSwarm`, `Swarm` |
|
|
4276
4303
|
| `@claude-flow/aidefence` | Threat detection | `isSafe`, `checkThreats`, `createAIDefence` |
|
|
4277
4304
|
| `@claude-flow/embeddings` | Vector embeddings | `createEmbeddingService` |
|
|
@@ -4287,7 +4314,7 @@ await hooks.endTrajectory(trajectory, { success: true });
|
|
|
4287
4314
|
|
|
4288
4315
|
## ๐ Ecosystem & Integrations
|
|
4289
4316
|
|
|
4290
|
-
Core infrastructure packages powering
|
|
4317
|
+
Core infrastructure packages powering Ruflo's intelligence layer.
|
|
4291
4318
|
|
|
4292
4319
|
<details>
|
|
4293
4320
|
<summary>โก <strong>Agentic-Flow Integration</strong> โ Core AI Infrastructure</summary>
|
|
@@ -4296,7 +4323,7 @@ Core infrastructure packages powering Claude-Flow's intelligence layer.
|
|
|
4296
4323
|
[](https://www.npmjs.com/package/agentic-flow)
|
|
4297
4324
|
[](https://github.com/ruvnet/agentic-flow)
|
|
4298
4325
|
|
|
4299
|
-
|
|
4326
|
+
Ruflo v3 is built on top of **[agentic-flow](https://github.com/ruvnet/agentic-flow)**, a production-ready AI agent orchestration platform. This deep integration provides 352x faster code transformations, learning memory, and geometric intelligence.
|
|
4300
4327
|
|
|
4301
4328
|
### Quick Start
|
|
4302
4329
|
|
|
@@ -4577,9 +4604,9 @@ claude mcp add agentic-flow -- npx agentic-flow mcp start
|
|
|
4577
4604
|
|
|
4578
4605
|
</details>
|
|
4579
4606
|
|
|
4580
|
-
### Integration with
|
|
4607
|
+
### Integration with Ruflo
|
|
4581
4608
|
|
|
4582
|
-
|
|
4609
|
+
Ruflo automatically leverages agentic-flow for:
|
|
4583
4610
|
|
|
4584
4611
|
| Feature | How It's Used |
|
|
4585
4612
|
|---------|---------------|
|
|
@@ -4590,7 +4617,7 @@ Claude-Flow automatically leverages agentic-flow for:
|
|
|
4590
4617
|
| **Embedding Search** | HNSW-indexed vector search (150x faster) |
|
|
4591
4618
|
|
|
4592
4619
|
```typescript
|
|
4593
|
-
//
|
|
4620
|
+
// Ruflo automatically uses agentic-flow optimizations
|
|
4594
4621
|
import { getTokenOptimizer } from '@claude-flow/integration';
|
|
4595
4622
|
|
|
4596
4623
|
const optimizer = await getTokenOptimizer();
|
|
@@ -4766,9 +4793,9 @@ jj.enableEncryption(key);
|
|
|
4766
4793
|
|
|
4767
4794
|
</details>
|
|
4768
4795
|
|
|
4769
|
-
###
|
|
4796
|
+
### Ruflo Skill
|
|
4770
4797
|
|
|
4771
|
-
|
|
4798
|
+
Ruflo includes a dedicated `/agentic-jujutsu` skill for AI-powered version control:
|
|
4772
4799
|
|
|
4773
4800
|
```bash
|
|
4774
4801
|
# Invoke the skill
|
|
@@ -4851,7 +4878,7 @@ npx agentic-jujutsu examples # Show usage examples
|
|
|
4851
4878
|
[](https://github.com/ruvnet/ruvector)
|
|
4852
4879
|
[](https://hub.docker.com/r/ruvnet/ruvector-postgres)
|
|
4853
4880
|
|
|
4854
|
-
**RuVector** is a high-performance distributed vector database combining vector search, graph queries, and self-learning neural networks. Written in Rust with Node.js/WASM bindings, it powers
|
|
4881
|
+
**RuVector** is a high-performance distributed vector database combining vector search, graph queries, and self-learning neural networks. Written in Rust with Node.js/WASM bindings, it powers Ruflo's intelligence layer with native speed.
|
|
4855
4882
|
|
|
4856
4883
|
### Key Capabilities
|
|
4857
4884
|
|
|
@@ -4933,7 +4960,7 @@ const compressed = ruvector.compress(embedding, 0.3); // 30% quality threshold
|
|
|
4933
4960
|
|
|
4934
4961
|
```bash
|
|
4935
4962
|
# Quick setup with CLI (recommended)
|
|
4936
|
-
npx
|
|
4963
|
+
npx ruflo ruvector setup --output ./my-ruvector
|
|
4937
4964
|
cd my-ruvector && docker-compose up -d
|
|
4938
4965
|
|
|
4939
4966
|
# Or pull directly from Docker Hub
|
|
@@ -4941,12 +4968,12 @@ docker run -d \
|
|
|
4941
4968
|
--name ruvector-postgres \
|
|
4942
4969
|
-p 5432:5432 \
|
|
4943
4970
|
-e POSTGRES_USER=claude \
|
|
4944
|
-
-e POSTGRES_PASSWORD=
|
|
4971
|
+
-e POSTGRES_PASSWORD=ruflo-test \
|
|
4945
4972
|
-e POSTGRES_DB=claude_flow \
|
|
4946
4973
|
ruvnet/ruvector-postgres
|
|
4947
4974
|
|
|
4948
4975
|
# Migrate existing memory to PostgreSQL
|
|
4949
|
-
npx
|
|
4976
|
+
npx ruflo ruvector import --input memory-export.json
|
|
4950
4977
|
```
|
|
4951
4978
|
|
|
4952
4979
|
**RuVector PostgreSQL vs pgvector:**
|
|
@@ -5103,12 +5130,12 @@ await db.createHyperedge(['agent-1', 'agent-2', 'agent-3'], {
|
|
|
5103
5130
|
|
|
5104
5131
|
</details>
|
|
5105
5132
|
|
|
5106
|
-
### Integration with
|
|
5133
|
+
### Integration with Ruflo
|
|
5107
5134
|
|
|
5108
|
-
|
|
5135
|
+
Ruflo automatically uses RuVector when available:
|
|
5109
5136
|
|
|
5110
5137
|
```typescript
|
|
5111
|
-
//
|
|
5138
|
+
// Ruflo detects and uses native ruvector
|
|
5112
5139
|
import { getVectorStore } from '@claude-flow/memory';
|
|
5113
5140
|
|
|
5114
5141
|
const store = await getVectorStore();
|
|
@@ -5126,19 +5153,19 @@ const similarity = attention.attention(queries, keys, values);
|
|
|
5126
5153
|
|
|
5127
5154
|
```bash
|
|
5128
5155
|
# RuVector PostgreSQL Setup (generates Docker files + SQL)
|
|
5129
|
-
npx
|
|
5130
|
-
npx
|
|
5131
|
-
npx
|
|
5156
|
+
npx ruflo ruvector setup # Output to ./ruvector-postgres
|
|
5157
|
+
npx ruflo ruvector setup --output ./mydir # Custom directory
|
|
5158
|
+
npx ruflo ruvector setup --print # Preview files
|
|
5132
5159
|
|
|
5133
5160
|
# Import from sql.js/JSON to PostgreSQL
|
|
5134
|
-
npx
|
|
5135
|
-
npx
|
|
5161
|
+
npx ruflo ruvector import --input data.json # Direct import
|
|
5162
|
+
npx ruflo ruvector import --input data.json --output sql # Dry-run (generate SQL)
|
|
5136
5163
|
|
|
5137
5164
|
# Other RuVector commands
|
|
5138
|
-
npx
|
|
5139
|
-
npx
|
|
5140
|
-
npx
|
|
5141
|
-
npx
|
|
5165
|
+
npx ruflo ruvector status --verbose # Check connection
|
|
5166
|
+
npx ruflo ruvector benchmark --vectors 10000 # Performance test
|
|
5167
|
+
npx ruflo ruvector optimize --analyze # Optimization suggestions
|
|
5168
|
+
npx ruflo ruvector backup --output backup.sql # Backup data
|
|
5142
5169
|
|
|
5143
5170
|
# Native ruvector CLI
|
|
5144
5171
|
npx ruvector status # Check installation
|
|
@@ -5165,11 +5192,11 @@ Cloud platform integration and deployment tools.
|
|
|
5165
5192
|
<details>
|
|
5166
5193
|
<summary>โ๏ธ <strong>Flow Nexus</strong> โ Cloud Platform Integration</summary>
|
|
5167
5194
|
|
|
5168
|
-
Flow Nexus is a **cloud platform** for deploying and scaling
|
|
5195
|
+
Flow Nexus is a **cloud platform** for deploying and scaling Ruflo beyond your local machine.
|
|
5169
5196
|
|
|
5170
5197
|
### What Flow Nexus Provides
|
|
5171
5198
|
|
|
5172
|
-
| Feature | Local
|
|
5199
|
+
| Feature | Local Ruflo | + Flow Nexus |
|
|
5173
5200
|
|---------|-------------------|--------------|
|
|
5174
5201
|
| **Swarm Scale** | 15 agents (local resources) | 100+ agents (cloud resources) |
|
|
5175
5202
|
| **Neural Training** | Limited by local GPU/CPU | Distributed GPU clusters |
|
|
@@ -5218,7 +5245,7 @@ Flow Nexus is a **cloud platform** for deploying and scaling Claude-Flow beyond
|
|
|
5218
5245
|
/flow-nexus-swarm
|
|
5219
5246
|
|
|
5220
5247
|
# Or via CLI
|
|
5221
|
-
npx
|
|
5248
|
+
npx ruflo@v3alpha nexus swarm deploy \
|
|
5222
5249
|
--topology hierarchical \
|
|
5223
5250
|
--max-agents 50 \
|
|
5224
5251
|
--region us-east-1
|
|
@@ -5230,13 +5257,13 @@ Isolated execution environments for running untrusted code:
|
|
|
5230
5257
|
|
|
5231
5258
|
```bash
|
|
5232
5259
|
# Create sandbox
|
|
5233
|
-
npx
|
|
5260
|
+
npx ruflo@v3alpha nexus sandbox create --language python
|
|
5234
5261
|
|
|
5235
5262
|
# Execute code safely
|
|
5236
|
-
npx
|
|
5263
|
+
npx ruflo@v3alpha nexus sandbox exec --code "print('Hello')"
|
|
5237
5264
|
|
|
5238
5265
|
# Cleanup
|
|
5239
|
-
npx
|
|
5266
|
+
npx ruflo@v3alpha nexus sandbox destroy
|
|
5240
5267
|
```
|
|
5241
5268
|
|
|
5242
5269
|
### Event-Driven Workflows
|
|
@@ -5262,10 +5289,10 @@ steps:
|
|
|
5262
5289
|
# 1. Sign up at flow-nexus.io
|
|
5263
5290
|
# 2. Get API key
|
|
5264
5291
|
# 3. Configure
|
|
5265
|
-
npx
|
|
5292
|
+
npx ruflo@v3alpha nexus configure --api-key <key>
|
|
5266
5293
|
|
|
5267
5294
|
# 4. Deploy
|
|
5268
|
-
npx
|
|
5295
|
+
npx ruflo@v3alpha nexus swarm deploy
|
|
5269
5296
|
```
|
|
5270
5297
|
|
|
5271
5298
|
</details>
|
|
@@ -5299,7 +5326,7 @@ Stream-Chain enables **sequential processing** where the output of one agent bec
|
|
|
5299
5326
|
/stream-chain
|
|
5300
5327
|
|
|
5301
5328
|
# Define pipeline
|
|
5302
|
-
npx
|
|
5329
|
+
npx ruflo@v3alpha stream-chain create \
|
|
5303
5330
|
--name "feature-pipeline" \
|
|
5304
5331
|
--stages "researcher,architect,coder,tester,reviewer"
|
|
5305
5332
|
```
|
|
@@ -5341,11 +5368,11 @@ stages:
|
|
|
5341
5368
|
|
|
5342
5369
|
```bash
|
|
5343
5370
|
# Run the pipeline
|
|
5344
|
-
npx
|
|
5371
|
+
npx ruflo@v3alpha stream-chain run feature-pipeline \
|
|
5345
5372
|
--input '{"requirements": "Add user dashboard with analytics"}'
|
|
5346
5373
|
|
|
5347
5374
|
# Monitor progress
|
|
5348
|
-
npx
|
|
5375
|
+
npx ruflo@v3alpha stream-chain status feature-pipeline
|
|
5349
5376
|
```
|
|
5350
5377
|
|
|
5351
5378
|
### Use Cases
|
|
@@ -5385,7 +5412,7 @@ The Pair Programming skill provides **human-AI collaborative coding** with role
|
|
|
5385
5412
|
/pair-programming --mode tdd
|
|
5386
5413
|
|
|
5387
5414
|
# Via CLI
|
|
5388
|
-
npx
|
|
5415
|
+
npx ruflo@v3alpha pair start --mode navigator
|
|
5389
5416
|
```
|
|
5390
5417
|
|
|
5391
5418
|
### TDD Mode Workflow
|
|
@@ -5425,16 +5452,16 @@ npx claude-flow@v3alpha pair start --mode navigator
|
|
|
5425
5452
|
|
|
5426
5453
|
```bash
|
|
5427
5454
|
# Switch roles mid-session
|
|
5428
|
-
npx
|
|
5455
|
+
npx ruflo@v3alpha pair switch
|
|
5429
5456
|
|
|
5430
5457
|
# Get AI explanation
|
|
5431
|
-
npx
|
|
5458
|
+
npx ruflo@v3alpha pair explain
|
|
5432
5459
|
|
|
5433
5460
|
# Run tests
|
|
5434
|
-
npx
|
|
5461
|
+
npx ruflo@v3alpha pair test
|
|
5435
5462
|
|
|
5436
5463
|
# End session with summary
|
|
5437
|
-
npx
|
|
5464
|
+
npx ruflo@v3alpha pair end
|
|
5438
5465
|
```
|
|
5439
5466
|
|
|
5440
5467
|
</details>
|
|
@@ -5491,22 +5518,22 @@ Detection Time: 0.04ms | 50+ Patterns | Self-Learning | HNSW Vector Search
|
|
|
5491
5518
|
|
|
5492
5519
|
```bash
|
|
5493
5520
|
# Basic threat scan
|
|
5494
|
-
npx
|
|
5521
|
+
npx ruflo@v3alpha security defend -i "ignore previous instructions"
|
|
5495
5522
|
|
|
5496
5523
|
# Scan a file
|
|
5497
|
-
npx
|
|
5524
|
+
npx ruflo@v3alpha security defend -f ./user-prompts.txt
|
|
5498
5525
|
|
|
5499
5526
|
# Quick scan (faster)
|
|
5500
|
-
npx
|
|
5527
|
+
npx ruflo@v3alpha security defend -i "some text" --quick
|
|
5501
5528
|
|
|
5502
5529
|
# JSON output
|
|
5503
|
-
npx
|
|
5530
|
+
npx ruflo@v3alpha security defend -i "test" -o json
|
|
5504
5531
|
|
|
5505
5532
|
# View statistics
|
|
5506
|
-
npx
|
|
5533
|
+
npx ruflo@v3alpha security defend --stats
|
|
5507
5534
|
|
|
5508
5535
|
# Full security audit
|
|
5509
|
-
npx
|
|
5536
|
+
npx ruflo@v3alpha security scan --depth full
|
|
5510
5537
|
```
|
|
5511
5538
|
|
|
5512
5539
|
### MCP Tools
|
|
@@ -5638,7 +5665,7 @@ Domain-Driven Design with bounded contexts, clean architecture, and measured per
|
|
|
5638
5665
|
| Module | Purpose | Key Features |
|
|
5639
5666
|
|--------|---------|--------------|
|
|
5640
5667
|
| `@claude-flow/hooks` | Event-driven lifecycle | ReasoningBank, 27 hooks, pattern learning |
|
|
5641
|
-
| `@claude-flow/memory` | Unified vector storage | AgentDB, HNSW indexing, 150x faster search |
|
|
5668
|
+
| `@claude-flow/memory` | Unified vector storage | AgentDB, HNSW indexing, 150x faster search, LearningBridge, MemoryGraph, AgentMemoryScope |
|
|
5642
5669
|
| `@claude-flow/security` | CVE remediation | Input validation, path security, AIDefence |
|
|
5643
5670
|
| `@claude-flow/swarm` | Multi-agent coordination | 6 topologies, Byzantine consensus, auto-scaling |
|
|
5644
5671
|
| `@claude-flow/plugins` | WASM extensions | RuVector plugins, semantic search, intent routing |
|
|
@@ -5670,6 +5697,12 @@ Domain-Driven Design with bounded contexts, clean architecture, and measured per
|
|
|
5670
5697
|
| **Swarm** | Agent spawn | <200ms | โ
150ms |
|
|
5671
5698
|
| **Swarm** | Consensus latency | <100ms | โ
75ms |
|
|
5672
5699
|
| **Neural** | SONA adaptation | <0.05ms | โ
0.03ms |
|
|
5700
|
+
| **Graph** | Build (1k nodes) | <200ms | โ
2.78ms (71.9x headroom) |
|
|
5701
|
+
| **Graph** | PageRank (1k nodes) | <100ms | โ
12.21ms (8.2x headroom) |
|
|
5702
|
+
| **Learning** | Insight recording | <5ms | โ
0.12ms (41x headroom) |
|
|
5703
|
+
| **Learning** | Consolidation | <500ms | โ
0.26ms (1,955x headroom) |
|
|
5704
|
+
| **Learning** | Confidence decay (1k) | <50ms | โ
0.23ms (215x headroom) |
|
|
5705
|
+
| **Transfer** | Knowledge transfer | <100ms | โ
1.25ms (80x headroom) |
|
|
5673
5706
|
| **Task** | Success rate | 95%+ | โ
100% (7/7) |
|
|
5674
5707
|
|
|
5675
5708
|
### Topology Performance
|
|
@@ -5692,7 +5725,7 @@ Domain-Driven Design with bounded contexts, clean architecture, and measured per
|
|
|
5692
5725
|
|
|
5693
5726
|
[](https://www.npmjs.com/package/@claude-flow/browser)
|
|
5694
5727
|
|
|
5695
|
-
AI-optimized browser automation integrating [agent-browser](https://github.com/AugmentCode/agent-browser) with
|
|
5728
|
+
AI-optimized browser automation integrating [agent-browser](https://github.com/AugmentCode/agent-browser) with ruflo for intelligent web automation, trajectory learning, and multi-agent browser coordination.
|
|
5696
5729
|
|
|
5697
5730
|
### Installation
|
|
5698
5731
|
|
|
@@ -5777,7 +5810,7 @@ const template = getWorkflow('login-basic');
|
|
|
5777
5810
|
<details>
|
|
5778
5811
|
<summary>๐ฆ <strong>Release Management</strong> โ @claude-flow/deployment</summary>
|
|
5779
5812
|
|
|
5780
|
-
Automated release management, versioning, and CI/CD for
|
|
5813
|
+
Automated release management, versioning, and CI/CD for Ruflo packages.
|
|
5781
5814
|
|
|
5782
5815
|
### Features
|
|
5783
5816
|
|
|
@@ -6091,10 +6124,10 @@ npm run bench:attention
|
|
|
6091
6124
|
npm run bench:startup
|
|
6092
6125
|
|
|
6093
6126
|
# Performance report
|
|
6094
|
-
npx
|
|
6127
|
+
npx ruflo@v3alpha performance report
|
|
6095
6128
|
|
|
6096
6129
|
# Benchmark specific suite
|
|
6097
|
-
npx
|
|
6130
|
+
npx ruflo@v3alpha performance benchmark --suite memory
|
|
6098
6131
|
```
|
|
6099
6132
|
|
|
6100
6133
|
</details>
|
|
@@ -6475,7 +6508,7 @@ export CLAUDE_FLOW_MEMORY_PATH="./data"
|
|
|
6475
6508
|
| `GCS_PROJECT_ID` | GCS project ID | Optional |
|
|
6476
6509
|
| `GOOGLE_CLOUD_PROJECT` | Alternative project ID variable | Optional |
|
|
6477
6510
|
| `GOOGLE_APPLICATION_CREDENTIALS` | Path to GCS service account JSON | Optional |
|
|
6478
|
-
| `GCS_PREFIX` | Prefix for stored files | `
|
|
6511
|
+
| `GCS_PREFIX` | Prefix for stored files | `ruflo-patterns` |
|
|
6479
6512
|
|
|
6480
6513
|
### Auto-Update System
|
|
6481
6514
|
|
|
@@ -6546,9 +6579,9 @@ CLAUDE_FLOW_HNSW_EF=200
|
|
|
6546
6579
|
|
|
6547
6580
|
### Configuration File Location
|
|
6548
6581
|
|
|
6549
|
-
|
|
6582
|
+
Ruflo looks for configuration in this order:
|
|
6550
6583
|
1. `./claude-flow.config.json` (project root)
|
|
6551
|
-
2. `~/.config/
|
|
6584
|
+
2. `~/.config/ruflo/config.json` (user config)
|
|
6552
6585
|
3. Environment variables (override any file config)
|
|
6553
6586
|
|
|
6554
6587
|
### Complete Configuration Schema
|
|
@@ -6648,7 +6681,7 @@ Claude Flow looks for configuration in this order:
|
|
|
6648
6681
|
"level": "info",
|
|
6649
6682
|
"format": "json",
|
|
6650
6683
|
"destination": "console",
|
|
6651
|
-
"filePath": "./logs/
|
|
6684
|
+
"filePath": "./logs/ruflo.log",
|
|
6652
6685
|
"maxFileSize": "100MB",
|
|
6653
6686
|
"maxFiles": 10
|
|
6654
6687
|
},
|
|
@@ -6715,7 +6748,7 @@ Claude Flow looks for configuration in this order:
|
|
|
6715
6748
|
"version": "3.0.0",
|
|
6716
6749
|
"memory": {
|
|
6717
6750
|
"type": "hybrid",
|
|
6718
|
-
"path": "/var/lib/
|
|
6751
|
+
"path": "/var/lib/ruflo/data",
|
|
6719
6752
|
"encryption": { "enabled": true, "algorithm": "aes-256-gcm" }
|
|
6720
6753
|
},
|
|
6721
6754
|
"swarm": { "topology": "hierarchical", "maxAgents": 15 },
|
|
@@ -6727,7 +6760,7 @@ Claude Flow looks for configuration in this order:
|
|
|
6727
6760
|
"level": "warn",
|
|
6728
6761
|
"format": "json",
|
|
6729
6762
|
"destination": "file",
|
|
6730
|
-
"filePath": "/var/log/
|
|
6763
|
+
"filePath": "/var/log/ruflo/production.log"
|
|
6731
6764
|
},
|
|
6732
6765
|
"monitoring": { "enabled": true, "metricsInterval": 30000 }
|
|
6733
6766
|
}
|
|
@@ -6771,25 +6804,25 @@ Claude Flow looks for configuration in this order:
|
|
|
6771
6804
|
|
|
6772
6805
|
```bash
|
|
6773
6806
|
# View current configuration
|
|
6774
|
-
npx
|
|
6807
|
+
npx ruflo@v3alpha config list
|
|
6775
6808
|
|
|
6776
6809
|
# Get specific value
|
|
6777
|
-
npx
|
|
6810
|
+
npx ruflo@v3alpha config get --key memory.type
|
|
6778
6811
|
|
|
6779
6812
|
# Set configuration value
|
|
6780
|
-
npx
|
|
6813
|
+
npx ruflo@v3alpha config set --key swarm.maxAgents --value 10
|
|
6781
6814
|
|
|
6782
6815
|
# Export configuration
|
|
6783
|
-
npx
|
|
6816
|
+
npx ruflo@v3alpha config export > my-config.json
|
|
6784
6817
|
|
|
6785
6818
|
# Import configuration
|
|
6786
|
-
npx
|
|
6819
|
+
npx ruflo@v3alpha config import --file my-config.json
|
|
6787
6820
|
|
|
6788
6821
|
# Reset to defaults
|
|
6789
|
-
npx
|
|
6822
|
+
npx ruflo@v3alpha config reset --key swarm
|
|
6790
6823
|
|
|
6791
6824
|
# Initialize with wizard
|
|
6792
|
-
npx
|
|
6825
|
+
npx ruflo@v3alpha init --wizard
|
|
6793
6826
|
```
|
|
6794
6827
|
|
|
6795
6828
|
</details>
|
|
@@ -6813,7 +6846,7 @@ lsof -i :3000
|
|
|
6813
6846
|
# Kill existing process
|
|
6814
6847
|
kill -9 <PID>
|
|
6815
6848
|
# Restart MCP server
|
|
6816
|
-
npx
|
|
6849
|
+
npx ruflo@v3alpha mcp start
|
|
6817
6850
|
```
|
|
6818
6851
|
|
|
6819
6852
|
**Agent spawn failures**
|
|
@@ -6827,9 +6860,9 @@ export CLAUDE_FLOW_MAX_AGENTS=5
|
|
|
6827
6860
|
**Pattern search returning no results**
|
|
6828
6861
|
```bash
|
|
6829
6862
|
# Verify patterns are stored
|
|
6830
|
-
npx
|
|
6863
|
+
npx ruflo@v3alpha hooks metrics
|
|
6831
6864
|
# Re-run pretraining if empty
|
|
6832
|
-
npx
|
|
6865
|
+
npx ruflo@v3alpha hooks pretrain
|
|
6833
6866
|
```
|
|
6834
6867
|
|
|
6835
6868
|
**Windows path issues**
|
|
@@ -6837,7 +6870,7 @@ npx claude-flow@v3alpha hooks pretrain
|
|
|
6837
6870
|
# Use forward slashes or escape backslashes
|
|
6838
6871
|
$env:CLAUDE_FLOW_MEMORY_PATH = "./data"
|
|
6839
6872
|
# Or use absolute path
|
|
6840
|
-
$env:CLAUDE_FLOW_MEMORY_PATH = "C:/Users/name/
|
|
6873
|
+
$env:CLAUDE_FLOW_MEMORY_PATH = "C:/Users/name/ruflo/data"
|
|
6841
6874
|
```
|
|
6842
6875
|
|
|
6843
6876
|
**Permission denied errors**
|
|
@@ -6850,7 +6883,7 @@ sudo chown -R $(whoami) ~/.npm
|
|
|
6850
6883
|
**High memory usage**
|
|
6851
6884
|
```bash
|
|
6852
6885
|
# Enable garbage collection
|
|
6853
|
-
node --expose-gc node_modules/.bin/
|
|
6886
|
+
node --expose-gc node_modules/.bin/ruflo
|
|
6854
6887
|
# Reduce HNSW parameters for lower memory
|
|
6855
6888
|
export CLAUDE_FLOW_HNSW_M=8
|
|
6856
6889
|
export CLAUDE_FLOW_HNSW_EF=100
|
|
@@ -6882,45 +6915,45 @@ export CLAUDE_FLOW_HNSW_EF=100
|
|
|
6882
6915
|
|
|
6883
6916
|
| Change | V2 | V3 | Impact |
|
|
6884
6917
|
|--------|----|----|--------|
|
|
6885
|
-
| **Package Structure** | `
|
|
6918
|
+
| **Package Structure** | `ruflo` | `@claude-flow/*` (scoped) | Update imports |
|
|
6886
6919
|
| **Memory Backend** | JSON files | AgentDB + HNSW | Faster search |
|
|
6887
6920
|
| **Hooks System** | Basic patterns | ReasoningBank + SONA | Self-learning |
|
|
6888
6921
|
| **Security** | Manual validation | Automatic strict mode | More secure |
|
|
6889
6922
|
| **CLI Commands** | Flat structure | Nested subcommands | New syntax |
|
|
6890
|
-
| **Config Format** | `.
|
|
6923
|
+
| **Config Format** | `.ruflo/config.json` | `claude-flow.config.json` | Update path |
|
|
6891
6924
|
|
|
6892
6925
|
### Step-by-Step Migration
|
|
6893
6926
|
|
|
6894
6927
|
```bash
|
|
6895
6928
|
# STEP 1: Backup existing data (CRITICAL)
|
|
6896
6929
|
cp -r ./data ./data-backup-v2
|
|
6897
|
-
cp -r ./.
|
|
6930
|
+
cp -r ./.ruflo ./.ruflo-backup-v2
|
|
6898
6931
|
|
|
6899
6932
|
# STEP 2: Check migration status
|
|
6900
|
-
npx
|
|
6933
|
+
npx ruflo@v3alpha migrate status
|
|
6901
6934
|
|
|
6902
6935
|
# STEP 3: Run migration with dry-run first
|
|
6903
|
-
npx
|
|
6936
|
+
npx ruflo@v3alpha migrate run --dry-run
|
|
6904
6937
|
|
|
6905
6938
|
# STEP 4: Execute migration
|
|
6906
|
-
npx
|
|
6939
|
+
npx ruflo@v3alpha migrate run --from v2
|
|
6907
6940
|
|
|
6908
6941
|
# STEP 5: Verify migration
|
|
6909
|
-
npx
|
|
6942
|
+
npx ruflo@v3alpha migrate verify
|
|
6910
6943
|
|
|
6911
6944
|
# STEP 6: Initialize V3 learning
|
|
6912
|
-
npx
|
|
6913
|
-
npx
|
|
6945
|
+
npx ruflo@v3alpha hooks pretrain
|
|
6946
|
+
npx ruflo@v3alpha doctor --fix
|
|
6914
6947
|
```
|
|
6915
6948
|
|
|
6916
6949
|
### Command Changes Reference
|
|
6917
6950
|
|
|
6918
6951
|
| V2 Command | V3 Command | Notes |
|
|
6919
6952
|
|------------|------------|-------|
|
|
6920
|
-
| `
|
|
6921
|
-
| `
|
|
6922
|
-
| `
|
|
6923
|
-
| `
|
|
6953
|
+
| `ruflo start` | `ruflo mcp start` | MCP is explicit |
|
|
6954
|
+
| `ruflo init` | `ruflo init --wizard` | Interactive mode |
|
|
6955
|
+
| `ruflo spawn <type>` | `ruflo agent spawn -t <type>` | Nested under `agent` |
|
|
6956
|
+
| `ruflo swarm create` | `ruflo swarm init --topology mesh` | Explicit topology |
|
|
6924
6957
|
| `--pattern-store path` | `--memory-backend agentdb` | Backend selection |
|
|
6925
6958
|
| `hooks record` | `hooks post-edit --success true` | Explicit success flag |
|
|
6926
6959
|
| `memory get <key>` | `memory retrieve --key <key>` | Explicit flag |
|
|
@@ -6930,7 +6963,7 @@ npx claude-flow@v3alpha doctor --fix
|
|
|
6930
6963
|
|
|
6931
6964
|
### Configuration Migration
|
|
6932
6965
|
|
|
6933
|
-
**V2 Config (`.
|
|
6966
|
+
**V2 Config (`.ruflo/config.json`)**:
|
|
6934
6967
|
```json
|
|
6935
6968
|
{
|
|
6936
6969
|
"mode": "basic",
|
|
@@ -6962,7 +6995,7 @@ npx claude-flow@v3alpha doctor --fix
|
|
|
6962
6995
|
|
|
6963
6996
|
```typescript
|
|
6964
6997
|
// V2 (deprecated)
|
|
6965
|
-
import { ClaudeFlow, Agent, Memory } from '
|
|
6998
|
+
import { ClaudeFlow, Agent, Memory } from 'ruflo';
|
|
6966
6999
|
|
|
6967
7000
|
// V3 (new)
|
|
6968
7001
|
import { ClaudeFlowClient } from '@claude-flow/cli';
|
|
@@ -6977,10 +7010,10 @@ If migration fails, you can rollback:
|
|
|
6977
7010
|
|
|
6978
7011
|
```bash
|
|
6979
7012
|
# Check rollback options
|
|
6980
|
-
npx
|
|
7013
|
+
npx ruflo@v3alpha migrate rollback --list
|
|
6981
7014
|
|
|
6982
7015
|
# Rollback to V2
|
|
6983
|
-
npx
|
|
7016
|
+
npx ruflo@v3alpha migrate rollback --to v2
|
|
6984
7017
|
|
|
6985
7018
|
# Restore backup manually if needed
|
|
6986
7019
|
rm -rf ./data
|
|
@@ -6989,12 +7022,12 @@ cp -r ./data-backup-v2 ./data
|
|
|
6989
7022
|
|
|
6990
7023
|
### Post-Migration Checklist
|
|
6991
7024
|
|
|
6992
|
-
- [ ] Verify all agents spawn correctly: `npx
|
|
6993
|
-
- [ ] Check memory search works: `npx
|
|
6994
|
-
- [ ] Confirm MCP server starts: `npx
|
|
6995
|
-
- [ ] Run doctor diagnostics: `npx
|
|
6996
|
-
- [ ] Test a simple swarm: `npx
|
|
6997
|
-
- [ ] Bootstrap learning: `npx
|
|
7025
|
+
- [ ] Verify all agents spawn correctly: `npx ruflo@v3alpha agent list`
|
|
7026
|
+
- [ ] Check memory search works: `npx ruflo@v3alpha memory search -q "test"`
|
|
7027
|
+
- [ ] Confirm MCP server starts: `npx ruflo@v3alpha mcp start`
|
|
7028
|
+
- [ ] Run doctor diagnostics: `npx ruflo@v3alpha doctor`
|
|
7029
|
+
- [ ] Test a simple swarm: `npx ruflo@v3alpha swarm init --topology mesh`
|
|
7030
|
+
- [ ] Bootstrap learning: `npx ruflo@v3alpha hooks pretrain`
|
|
6998
7031
|
|
|
6999
7032
|
### Common Migration Issues
|
|
7000
7033
|
|