ruflo 3.52.1 โ 3.54.0
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/README.md +141 -44
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -1,24 +1,85 @@
|
|
|
1
1
|
<div align="center">
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
<a href="https://cognitum.one/agentic-engineering"><img src="ruflo/assets/ruflo-neon-flicker.gif" alt="Ruflo animated neon sign" width="100%"></a>
|
|
4
|
+
|
|
5
|
+
**An agent meta-harness for Claude Code and Codex.**
|
|
4
6
|
|
|
5
7
|
<!-- Try Ruflo โ the 3 badges first-time visitors actually act on -->
|
|
6
8
|
[](https://www.npmjs.com/package/ruflo)
|
|
7
9
|
[](https://opensource.org/licenses/MIT)
|
|
8
10
|
[](https://github.com/ruvnet/claude-flow)
|
|
9
11
|
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
|
|
12
|
+
<p align="center">
|
|
13
|
+
<a href="data/npm-downloads.latest.json"><img src="docs/assets/readme/badges/downloads.svg?v=mobile-readable-3" width="300" alt="Ecosystem npm downloads: 12.52M over 12 months through October 4, 2026"></a>
|
|
14
|
+
<br>
|
|
15
|
+
<a href="https://github.com/ruvnet/claude-flow"><img src="docs/assets/readme/badges/claude.svg?v=mobile-readable-3" width="300" alt="Claude Code"></a>
|
|
16
|
+
<a href="https://www.npmjs.com/package/@claude-flow/codex"><img src="docs/assets/readme/badges/codex.svg?v=mobile-readable-3" width="300" alt="Codex Plugin"></a>
|
|
17
|
+
</p>
|
|
18
|
+
|
|
19
|
+
</div>
|
|
20
|
+
|
|
21
|
+
<a id="start-here"></a>
|
|
22
|
+
|
|
23
|
+
## <img src="docs/assets/readme/icons/terminal.svg" width="32" height="32" alt=""> Get started with Ruflo
|
|
24
|
+
|
|
25
|
+
<img src="docs/assets/readme/icons/plugins.svg" width="28" height="28" alt=""> **Start in Claude Code** with core tools, the visual console and runtime mods. Requires Claude Code **2.1.287 or later**. Run inside Claude Code:
|
|
26
|
+
|
|
27
|
+
```text
|
|
28
|
+
/plugin marketplace add ruvnet/ruflo
|
|
29
|
+
/plugin install ruflo-core@ruflo
|
|
30
|
+
/plugin install ruflo-console@ruflo
|
|
31
|
+
/plugin install ruflo-mods@ruflo
|
|
32
|
+
/reload-plugins
|
|
33
|
+
/ruflo
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
**Core** provides foundation tools. **Console** opens the agent cockpit. **Mods** add routing and policy enforcement inside Claude Code. Mods run with your account's permissions; review their code before installing.
|
|
37
|
+
|
|
38
|
+
<img src="docs/assets/readme/icons/terminal.svg" width="28" height="28" alt=""> **Using Codex or another MCP enabled tool?** Use NPX for Ruflo project setup and connect your client to the Ruflo MCP server. Run the setup wizard in your project terminal:
|
|
39
|
+
|
|
40
|
+
```bash
|
|
41
|
+
npx ruflo@latest init wizard
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
For clients that support local stdio MCP servers, configure **command** `npx` and **arguments** `["-y", "ruflo@latest", "mcp", "start"]`. The equivalent server command is:
|
|
45
|
+
|
|
46
|
+
```bash
|
|
47
|
+
npx -y ruflo@latest mcp start
|
|
48
|
+
```
|
|
49
|
+
|
|
50
|
+
MCP exposes Ruflo tools to your client. The console and mods above are Claude Code integrations; hook support depends on the client.
|
|
51
|
+
|
|
52
|
+
[Compare install paths](#quick-start) ยท [Open the console](#console-walkthrough) ยท [User guide](docs/USERGUIDE.md)
|
|
53
|
+
|
|
54
|
+
<div align="center">
|
|
55
|
+
|
|
56
|
+
|
|
57
|
+
### Optional: ruOS Desktop
|
|
58
|
+
|
|
59
|
+
<a href="https://ruos.cognitum.one"><img src="ruflo/assets/ruos-animated.svg" alt="ruOS โ A desktop that runs itself" width="100%"></a>
|
|
60
|
+
|
|
61
|
+
**Connect ruOS to ChatGPT or Claude via MCP:**
|
|
62
|
+
|
|
63
|
+
```text
|
|
64
|
+
https://ruos.cognitum.one/mcp
|
|
65
|
+
```
|
|
66
|
+
|
|
67
|
+
|
|
68
|
+
|
|
69
|
+
<!-- RuVector promo -->
|
|
70
|
+
<a href="https://github.com/ruvnet/ruvector"><img src="docs/assets/readme/ruvector-promo-depth.svg" width="100%" alt="RuVector: Give your agents memory. Local vector search, persistent context, graph relationships and feedback learning. Explore RuVector."></a>
|
|
71
|
+
|
|
72
|
+
```bash
|
|
73
|
+
npx ruvector
|
|
74
|
+
```
|
|
75
|
+
|
|
76
|
+
|
|
77
|
+
|
|
16
78
|
|
|
17
79
|
# Ruflo
|
|
18
80
|
|
|
19
81
|
[English](README.md) ยท [็ฎไฝไธญๆ](README.zh-CN.md)
|
|
20
82
|
|
|
21
|
-
**An agent meta-harness for Claude Code and Codex.**
|
|
22
83
|
|
|
23
84
|
[](docs/ruflo-explained.md)
|
|
24
85
|
|
|
@@ -31,13 +92,16 @@ A 14-chapter guide: from the basic idea to a first useful task, then memory, age
|
|
|
31
92
|
|
|
32
93
|
One `npx ruflo init` gives Claude Code a nervous system: agents self-organize into swarms, learn from every task, remember across sessions, and โ with federation โ securely talk to agents on other machines without leaking data. You keep writing code. Ruflo handles the coordination.
|
|
33
94
|
|
|
34
|
-
|
|
35
|
-
Self-Learning / Self-Optimizing Agent Architecture
|
|
95
|
+
<p align="center"><img src="docs/assets/readme/learning-cinematic-compact.svg" width="100%" alt="Ruflo trajectory learning: branching memory paths, outcome feedback, contrastive AI and local learning. No LLM required for local vector retrieval and contrastive updates; agent execution may still use an LLM."></p>
|
|
36
96
|
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
97
|
+
<sub>Conceptual learning loop. Local vector retrieval and contrastive updates can run without an LLM; embeddings and configured learning modules are still required. See the <a href="v3/@claude-flow/cli/src/services/ruvector-training.ts">RuVector training integration</a> and <a href="v3/@claude-flow/neural/src/modes/balanced.ts">trajectory contrastive learning</a>.</sub>
|
|
98
|
+
|
|
99
|
+
<details>
|
|
100
|
+
<summary>Architecture in text</summary>
|
|
101
|
+
|
|
102
|
+
User โ Ruflo (CLI/MCP) โ Router โ Swarm โ Agents โ Memory โ LLM providers. Memory feeds useful experience back into routing. This is a conceptual flow, not a live execution trace.
|
|
103
|
+
|
|
104
|
+
</details>
|
|
41
105
|
|
|
42
106
|
> **New to Ruflo?** You don't need to learn 314 MCP tools or 26 CLI commands. After `init`, just use Claude Code normally โ the hooks system automatically routes tasks, learns from successful patterns, and coordinates agents in the background.
|
|
43
107
|
|
|
@@ -50,15 +114,34 @@ User --> Ruflo (CLI/MCP) --> Router --> Swarm --> Agents --> Memory --> LLM Prov
|
|
|
50
114
|
|
|
51
115
|
---
|
|
52
116
|
|
|
53
|
-
<p align="center"><img src="docs/assets/
|
|
117
|
+
<p align="center"><img src="docs/assets/readme/console.svg" alt="Mission control: inspect agent work" width="100%"></p>
|
|
118
|
+
|
|
119
|
+
<p align="center"><img src="docs/assets/ruflo-console-workflows.svg" width="952" height="964" alt="An animated recording of the ruflo console inside Claude Code: the boot (the neon sign and every area checked), then the Workflows page on a sample run: phases and agents with model, tokens and time; drilling from a run into one agent's activity, log and result; search; failure triage; cost; replay and compare; the control tab with a confirm card; and the mission autopilot panel"></p>
|
|
120
|
+
|
|
121
|
+
<img src="docs/assets/readme/console-icon-workflows.svg" width="28" height="28" alt=""> **Your agent cockpit.** Track workflows, agents, models, tokens and cost beside Claude Code. The animation shows startup checks and a **sample workflow**, not a live session.
|
|
122
|
+
|
|
123
|
+
<img src="docs/assets/readme/console-icon-inspect.svg" width="28" height="28" alt=""> **Inspect any run.** Open agent logs and results, search, triage failures, replay and compare. Start with `npx ruflo init`, restart Claude Code, then `/ruflo`. [Full console tour](docs/assets/ruflo-console-walkthrough-wide.gif).
|
|
54
124
|
|
|
55
|
-
<
|
|
125
|
+
<img src="docs/assets/readme/console-icon-control.svg" width="28" height="28" alt=""> **Let Claude drive. You set the limits.** Enable **Settings โ Claude control** to navigate and run console actions. Choose `read`, `write`, `manage` or `full`, with `ask` or `auto` approval. The current default is **read + ask**; raising the level is your choice. Actions above your permission level are refused, and network, spending and destructive actions require confirmation even in `auto`. Review the live action log or press **Take back control** to stop Claude control. [Details](v3/docs/adr/ADR-444-claude-controls-the-console.md).
|
|
56
126
|
|
|
57
|
-
|
|
127
|
+
<a id="console-walkthrough"></a>
|
|
128
|
+
|
|
129
|
+
### One task: create a mission with Claude
|
|
130
|
+
|
|
131
|
+
<img src="docs/assets/readme/console-icon-workflows.svg" width="28" height="28" alt=""> **Watch the recorded console session below.** Claude creates a mission, opens the Learning and Security pages, and reports its actions in Overview.
|
|
132
|
+
|
|
133
|
+
1. **Set the boundary.** Install the console using the commands below, open `/ruflo`, then choose **Settings โ Claude control โ write + ask**.
|
|
134
|
+
2. **Give a concrete request.** Try: โCreate a mission to add a dark mode toggle. Show me the mission and its status.โ
|
|
135
|
+
3. **Approve creation.** Claude opens Missions and sets the goal. Confirm the pending create action in the console.
|
|
136
|
+
4. **Verify the result.** Check that Missions contains the goal and Overview records the action. Creating a mission does not mean the feature has been implemented.
|
|
137
|
+
5. **Keep control.** **Take back control** pauses Claude's console tools. A later call should be refused until you restore control.
|
|
138
|
+
|
|
139
|
+
**What the recording demonstrates:** a real Claude Haiku session with `write + auto`, mission creation, page navigation, a refused swarm stop, and control being taken back. The steps above use `ask` so you approve creation yourself. The separate workflow animation uses sample data; neither is evidence of completed swarm work or memory recall.
|
|
140
|
+
|
|
141
|
+
[Implementation and recorded test findings](v3/docs/adr/ADR-444-claude-controls-the-console.md) ยท [Reproduction script](plugins/ruflo-console/scripts/e2e-control.sh)
|
|
58
142
|
|
|
59
143
|
<p align="center"><img src="docs/assets/ruflo-console-claude-control.gif" alt="Claude Code with the ruflo console beside it: Claude sets a mission goal, creates the mission and opens the Learning, Security and Overview pages through the console tools; the Claude control dashboard logs each action; swarm-stop is refused because it needs the full level; the person clicks Take back control and the next request is refused"></p>
|
|
60
144
|
|
|
61
|
-
<sub>A real recording (Claude Haiku, a few cents): control set to <code>write</code> with auto-confirm. Setting a goal and creating the mission is within that level; stopping a swarm needs <code>full</code>, so it is refused; after <b>Take back control</b> every call is refused.</sub>
|
|
62
145
|
|
|
63
146
|
**Install the mods from the ruflo marketplace** (Claude Code 2.1.287 or later; mods run with your account's permissions and are not sandboxed, so read the code first):
|
|
64
147
|
|
|
@@ -73,6 +156,8 @@ User --> Ruflo (CLI/MCP) --> Router --> Swarm --> Agents --> Memory --> LLM Prov
|
|
|
73
156
|
|
|
74
157
|
## Quick Start
|
|
75
158
|
|
|
159
|
+
<p align="center"><img src="docs/assets/readme/quick-start.svg" alt="Start building with Ruflo" width="100%"></p>
|
|
160
|
+
|
|
76
161
|
There are **two different install paths** with very different surface areas. Pick based on what you need (#1744):
|
|
77
162
|
|
|
78
163
|
| | **Claude Code Plugin** | **CLI install (`npx ruflo init`)** |
|
|
@@ -183,7 +268,7 @@ This adds slash commands and agent definitions. `ruflo-core` (installed above) d
|
|
|
183
268
|
|
|
184
269
|
</details>
|
|
185
270
|
|
|
186
|
-
### CLI Install
|
|
271
|
+
### <img src="docs/assets/readme/icons/terminal.svg" width="28" height="28" alt=""> CLI Install
|
|
187
272
|
|
|
188
273
|
**macOS / Linux / WSL / Git-Bash:**
|
|
189
274
|
|
|
@@ -207,7 +292,7 @@ npm install -g ruflo@latest
|
|
|
207
292
|
|
|
208
293
|
> ๐ก **Windows users:** the `curl ... | bash` form needs a POSIX shell (Git-Bash, WSL, MSYS). The `npx ruflo@latest init wizard` line works natively in PowerShell and cmd. If you hit an `'bash' is not recognized` error, use the `npx` line instead โ both end up running the same init flow.
|
|
209
294
|
|
|
210
|
-
### MCP Server
|
|
295
|
+
### <img src="docs/assets/readme/icons/network.svg" width="28" height="28" alt=""> MCP Server
|
|
211
296
|
|
|
212
297
|
```bash
|
|
213
298
|
# Add Ruflo as an MCP server in Claude Code
|
|
@@ -218,35 +303,39 @@ claude mcp add claude-flow -- npx ruflo@latest mcp start
|
|
|
218
303
|
|
|
219
304
|
## What You Get
|
|
220
305
|
|
|
306
|
+
<p align="center"><img src="docs/assets/readme/capabilities.svg" alt="Your agent toolkit" width="100%"></p>
|
|
307
|
+
|
|
308
|
+
<table>
|
|
309
|
+
<tr><td width="50%"><a href="plugins/ruflo-swarm/README.md"><img src="docs/assets/readme/card-swarm.svg" width="100%" alt="Agent teams"></a></td><td width="50%"><a href="plugins/ruflo-rag-memory/README.md"><img src="docs/assets/readme/card-memory.svg" width="100%" alt="Persistent memory"></a></td></tr>
|
|
310
|
+
<tr><td width="50%"><a href="plugins/ruflo-intelligence/README.md"><img src="docs/assets/readme/card-learning.svg" width="100%" alt="Learning loops"></a></td><td width="50%"><a href="plugins/ruflo-security-audit/README.md"><img src="docs/assets/readme/card-security.svg" width="100%" alt="Security controls"></a></td></tr>
|
|
311
|
+
<tr><td width="50%"><a href="https://ruvnet.github.io/ruflo"><img src="docs/assets/readme/card-plugins.svg" width="100%" alt="Plugin marketplace"></a></td><td width="50%"><a href="plugins/ruflo-ruvllm/README.md"><img src="docs/assets/readme/card-routing.svg" width="100%" alt="Models and routing"></a></td></tr>
|
|
312
|
+
</table>
|
|
313
|
+
|
|
221
314
|
| Capability | Description |
|
|
222
315
|
|------------|-------------|
|
|
223
|
-
|
|
|
224
|
-
|
|
|
225
|
-
|
|
|
226
|
-
|
|
|
227
|
-
|
|
|
228
|
-
|
|
|
229
|
-
|
|
|
230
|
-
|
|
|
231
|
-
|
|
|
232
|
-
|
|
|
233
|
-
|
|
|
316
|
+
| <img src="docs/assets/readme/icons/agents.svg" width="28" height="28" alt=""> **100+ Agents** | Specialized agents for coding, testing, security, docs, architecture |
|
|
317
|
+
| <img src="docs/assets/readme/icons/network.svg" width="28" height="28" alt=""> **Comms Layer** | Zero-trust federation โ agents across machines/orgs discover, authenticate, and exchange work securely |
|
|
318
|
+
| <img src="docs/assets/readme/icons/swarm.svg" width="28" height="28" alt=""> **Swarm Coordination** | Hierarchical, mesh, and adaptive topologies with consensus |
|
|
319
|
+
| <img src="docs/assets/readme/icons/learning.svg" width="28" height="28" alt=""> **Self-Learning** | SONA neural patterns, ReasoningBank, trajectory learning |
|
|
320
|
+
| <img src="docs/assets/readme/icons/memory.svg" width="28" height="28" alt=""> **Vector Memory** | HNSW-indexed AgentDB โ measured ~1.9x faster at N=20k, ~3.2xโ4.7x at N=5k vs brute force (recall@10 ~0.99); ANN wins above the crossover, ties/loses at small N. See [audit](docs/reviews/intelligence-system-audit-2026-05-29.md) + [`scripts/benchmark-intelligence.mjs`](scripts/benchmark-intelligence.mjs) |
|
|
321
|
+
| <img src="docs/assets/readme/icons/workers.svg" width="28" height="28" alt=""> **Background Workers** | 12 auto-triggered workers (audit, optimize, testgaps, etc.) |
|
|
322
|
+
| <img src="docs/assets/readme/icons/plugins.svg" width="28" height="28" alt=""> **Plugin Marketplace** | 33 native Claude Code plugins + 21 npm plugins |
|
|
323
|
+
| <img src="docs/assets/readme/icons/routing.svg" width="28" height="28" alt=""> **Multi-Provider** | Claude, GPT, Gemini, Cohere, Ollama with smart routing |
|
|
324
|
+
| <img src="docs/assets/readme/icons/security.svg" width="28" height="28" alt=""> **Security** | AIDefence, input validation, CVE remediation, path traversal prevention |
|
|
325
|
+
| <img src="docs/assets/readme/icons/federation.svg" width="28" height="28" alt=""> **Agent Federation** | Cross-installation agent collaboration with zero-trust security |
|
|
326
|
+
| <img src="docs/assets/readme/icons/audit.svg" width="28" height="28" alt=""> **[MetaHarness](docs/metaharness-user-guide.md)** | Audit your AI agent setup before you ship. Grade readiness (1-100), scan tool configs for security issues, snapshot the whole project to catch regressions over time, and find templates that match your repo. `ruflo eject` turns a ruflo project into a standalone agent toolkit with its own name. [Full guide](docs/metaharness-user-guide.md). |
|
|
327
|
+
|
|
328
|
+
### <img src="docs/assets/readme/icons/learning.svg" width="28" height="28" alt=""> Learning from experience
|
|
329
|
+
|
|
330
|
+
<p align="center"><img src="docs/assets/readme/learning-flow.svg" width="100%" alt="Recall, execute, evaluate, store, adapt and reuse: an illustrative agent learning cycle."></p>
|
|
331
|
+
|
|
332
|
+
Useful trajectories and task feedback can inform future work. Results depend on the configured memory, learning components and quality of feedback. [Learning plugin](plugins/ruflo-intelligence/README.md).
|
|
234
333
|
|
|
235
334
|
### Agent Federation โ Slack for Agents
|
|
236
335
|
|
|
237
|
-
|
|
238
|
-
|
|
239
|
-
|
|
240
|
-
keys stripped from you in transit
|
|
241
|
-
|
|
|
242
|
-
v
|
|
243
|
-
Their Agent <-- [ Block attacks ] <-- [ Check identity ] <------+
|
|
244
|
-
Stops prompt Rejects forgeries
|
|
245
|
-
injection
|
|
246
|
-
|
|
247
|
-
Audit trail on both sides.
|
|
248
|
-
Trust builds over time. Bad behavior = instant downgrade.
|
|
249
|
-
```
|
|
336
|
+
<p align="center"><img src="docs/assets/readme/federation.svg" alt="Connected intelligence across machines" width="100%"></p>
|
|
337
|
+
|
|
338
|
+
<p align="center"><img src="docs/assets/readme/federation-flow.svg" width="100%" alt="Outbound agent, data filtering, signing and encryption, identity verification, input checks and receiving agent."></p>
|
|
250
339
|
|
|
251
340
|
Slack gave teams channels. Federation gives agents the same thing โ **shared workspaces across trust boundaries**, where agents on different machines, orgs, or cloud regions can discover each other, prove who they are, and collaborate on tasks.
|
|
252
341
|
|
|
@@ -348,6 +437,8 @@ User --> Claude Code / CLI
|
|
|
348
437
|
|
|
349
438
|
## Documentation
|
|
350
439
|
|
|
440
|
+
<p align="center"><img src="docs/assets/readme/documentation.svg" alt="Guides, architecture and verification" width="100%"></p>
|
|
441
|
+
|
|
351
442
|
Four docs for four audiences:
|
|
352
443
|
|
|
353
444
|
| Doc | When to read it |
|
|
@@ -378,6 +469,8 @@ User Guide section index:
|
|
|
378
469
|
|
|
379
470
|
## Support
|
|
380
471
|
|
|
472
|
+
<p align="center"><img src="docs/assets/readme/support.svg" alt="Build with the Ruflo community" width="100%"></p>
|
|
473
|
+
|
|
381
474
|
| Resource | Link |
|
|
382
475
|
|----------|------|
|
|
383
476
|
| Documentation | [User Guide](docs/USERGUIDE.md) |
|
|
@@ -386,6 +479,10 @@ User Guide section index:
|
|
|
386
479
|
| Community | [Agentics Foundation Discord](https://discord.com/invite/dfxmpwkG2D) |
|
|
387
480
|
| Powered by | [Cognitum.one](https://cognitum.one) |
|
|
388
481
|
|
|
482
|
+
<p align="center"><img src="docs/assets/readme/signal-divider.svg" alt="Ruflo" width="100%"></p>
|
|
483
|
+
|
|
389
484
|
## License
|
|
390
485
|
|
|
391
486
|
MIT - [RuvNet](https://github.com/ruvnet)
|
|
487
|
+
|
|
488
|
+
<a href="https://cognitum.one"><img src="docs/assets/readme/cognitum-banner-v2.svg" width="100%" alt="Cognitum One: Ambient Intelligence at the edge of the Physical World. Explore cognitum.one."></a>
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "ruflo",
|
|
3
|
-
"version": "3.
|
|
3
|
+
"version": "3.54.0",
|
|
4
4
|
"description": "Ruflo - Enterprise AI agent orchestration platform. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration",
|
|
5
5
|
"main": "bin/ruflo.js",
|
|
6
6
|
"type": "module",
|
|
@@ -40,7 +40,7 @@
|
|
|
40
40
|
"package:rvf": "bash src/scripts/package-rvf.sh"
|
|
41
41
|
},
|
|
42
42
|
"dependencies": {
|
|
43
|
-
"@claude-flow/cli": "^3.
|
|
43
|
+
"@claude-flow/cli": "^3.54.0"
|
|
44
44
|
},
|
|
45
45
|
"optionalDependencies": {},
|
|
46
46
|
"overrides": {
|