network-ai 4.0.16 → 4.0.17

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.
Files changed (4) hide show
  1. package/README.md +44 -36
  2. package/dist/index.d.ts +1 -1
  3. package/dist/index.js +1 -1
  4. package/package.json +1 -1
package/README.md CHANGED
@@ -1,10 +1,10 @@
1
- # Network-AI
1
+ # Network-AI
2
2
 
3
3
  **TypeScript/Node.js multi-agent orchestrator — shared state, guardrails, budgets, and cross-framework coordination**
4
4
 
5
5
  [![CI](https://github.com/jovanSAPFIONEER/Network-AI/actions/workflows/ci.yml/badge.svg)](https://github.com/jovanSAPFIONEER/Network-AI/actions/workflows/ci.yml)
6
6
  [![CodeQL](https://github.com/jovanSAPFIONEER/Network-AI/actions/workflows/codeql.yml/badge.svg)](https://github.com/jovanSAPFIONEER/Network-AI/actions/workflows/codeql.yml)
7
- [![Release](https://img.shields.io/badge/release-v4.0.16-blue.svg)](https://github.com/jovanSAPFIONEER/Network-AI/releases)
7
+ [![Release](https://img.shields.io/badge/release-v4.0.17-blue.svg)](https://github.com/jovanSAPFIONEER/Network-AI/releases)
8
8
  [![npm](https://img.shields.io/npm/dw/network-ai.svg?label=npm%20downloads)](https://www.npmjs.com/package/network-ai)
9
9
  [![Tests](https://img.shields.io/badge/tests-1184%20passing-brightgreen.svg)](#testing)
10
10
  [![Adapters](https://img.shields.io/badge/frameworks-12%20supported-blueviolet.svg)](#adapter-system)
@@ -44,31 +44,37 @@ Network-AI is a TypeScript/Node.js multi-agent orchestrator that adds coordinati
44
44
 
45
45
  ## Architecture
46
46
 
47
+ ```mermaid
48
+ %%{init: {'theme': 'base', 'themeVariables': {'primaryColor': '#1e293b', 'primaryTextColor': '#e2e8f0', 'primaryBorderColor': '#475569', 'lineColor': '#94a3b8', 'clusterBkg': '#0f172a', 'clusterBorder': '#334155', 'edgeLabelBackground': '#1e293b', 'edgeLabelColor': '#cbd5e1', 'titleColor': '#e2e8f0'}}}%%
49
+ flowchart TD
50
+ classDef app fill:#1e3a5f,stroke:#3b82f6,color:#bfdbfe,font-weight:bold
51
+ classDef security fill:#451a03,stroke:#d97706,color:#fde68a
52
+ classDef routing fill:#14532d,stroke:#16a34a,color:#bbf7d0
53
+ classDef quality fill:#3b0764,stroke:#9333ea,color:#e9d5ff
54
+ classDef blackboard fill:#0c4a6e,stroke:#0284c7,color:#bae6fd
55
+ classDef adapters fill:#064e3b,stroke:#059669,color:#a7f3d0
56
+ classDef audit fill:#1e293b,stroke:#475569,color:#94a3b8
57
+
58
+ App["Your Application"]:::app
59
+ App -->|"createSwarmOrchestrator()"| SO
60
+
61
+ subgraph SO["SwarmOrchestrator"]
62
+ AG["AuthGuardian\n(permission gating)"]:::security
63
+ AR["AdapterRegistry\n(route tasks to frameworks)"]:::routing
64
+ QG["QualityGateAgent\n(validate blackboard writes)"]:::quality
65
+ BB["SharedBlackboard\n(shared agent state)\npropose → validate → commit\nfilesystem mutex"]:::blackboard
66
+ AD["Adapters — plug any framework in, swap freely\nLangChain · AutoGen · CrewAI · MCP · LlamaIndex · …"]:::adapters
67
+
68
+ AG -->|"grant / deny"| AR
69
+ AR -->|"tasks dispatched"| AD
70
+ AD -->|"writes results"| BB
71
+ QG -->|"validates"| BB
72
+ end
73
+
74
+ SO --> AUDIT["data/audit_log.jsonl"]:::audit
47
75
  ```
48
- ┌─────────────────────────────────────────────────────────────┐
49
- │ Your Application │
50
- └──────────────────────────┬──────────────────────────────────┘
51
- │ createSwarmOrchestrator()
52
- ┌──────────────────────────▼──────────────────────────────────┐
53
- │ SwarmOrchestrator │
54
- │ ┌──────────────┐ ┌───────────────┐ ┌─────────────────┐ │
55
- │ │ AdapterRegistry│ │ AuthGuardian │ │ FederatedBudget │ │
56
- │ │ (route tasks) │ │ (permissions) │ │ (token ceilings)│ │
57
- │ └──────┬───────┘ └───────────────┘ └─────────────────┘ │
58
- │ │ │
59
- │ ┌──────▼──────────────────────────────────────────────┐ │
60
- │ │ LockedBlackboard (shared state) │ │
61
- │ │ propose → validate → commit (file-system mutex) │ │
62
- │ └──────────────────────────────────────────────────────┘ │
63
- │ │ │
64
- │ ┌──────▼───────────────────────────────────────────────┐ │
65
- │ │ Adapters (plug any framework in, swap out freely) │ │
66
- │ │ LangChain │ AutoGen │ CrewAI │ MCP │ LlamaIndex │… │ │
67
- │ └──────────────────────────────────────────────────────┘ │
68
- └─────────────────────────────────────────────────────────────┘
69
- │
70
- HMAC-signed audit log
71
- ```
76
+
77
+ > `FederatedBudget` is a standalone export — instantiate it separately and optionally wire it to a blackboard backend for cross-node token budget enforcement.
72
78
 
73
79
  → [Full architecture, FSM journey, and handoff protocol](ARCHITECTURE.md)
74
80
 
@@ -129,13 +135,15 @@ Add budgets, permissions, and cross-framework agents with the same pattern. →
129
135
 
130
136
  ## Demo — Control-Plane Stress Test *(no API key)*
131
137
 
132
- Runs in ~2 seconds. Proves the coordination primitives without any LLM calls.
138
+ Runs in ~3 seconds. Proves the coordination primitives without any LLM calls.
133
139
 
134
140
  ```bash
135
141
  npm run demo -- --08
136
142
  ```
137
143
 
138
- What it shows: atomic blackboard locking, priority preemption (priority-3 wins over priority-0 on same key), FSM hard-stop at 700 ms, live compliance violation capture (TOOL_ABUSE, TURN_TAKING, RESPONSE_TIMEOUT, JOURNEY_TIMEOUT), and `FederatedBudget` tracking — all without a single API call.
144
+ What it shows: atomic blackboard locking, priority preemption (priority-3 wins over priority-0 on same key), **AuthGuardian permission gate** (blocked → justified → granted with token), FSM hard-stop at 700 ms, live compliance violation capture (TOOL_ABUSE, TURN_TAKING, RESPONSE_TIMEOUT, JOURNEY_TIMEOUT), and `FederatedBudget` tracking — all without a single API call.
145
+
146
+ [![Control Plane Demo](https://img.youtube.com/vi/niVRZJu1MEo/0.jpg)](https://www.youtube.com/watch?v=niVRZJu1MEo)
139
147
 
140
148
  **8-agent AI pipeline** (requires `OPENAI_API_KEY` — builds a Payment Processing Service end-to-end):
141
149
 
@@ -176,12 +184,12 @@ Extend `BaseAdapter` to add your own in minutes. See [references/adapter-system.
176
184
 
177
185
  | Capability | Network-AI | LangGraph | CrewAI | AutoGen |
178
186
  |---|---|---|---|---|
179
- | Cross-framework agents in one swarm | ✅ 12 adapters | ❌ LangChain only | ❌ CrewAI only | ❌ AutoGen only |
180
- | Atomic shared state (conflict-safe) | ✅ `propose → validate → commit` | ⚠️ Last-write-wins | ⚠️ Last-write-wins | ⚠️ Last-write-wins |
181
- | Hard budget ceiling per agent | ✅ `FederatedBudget` | ⚠️ Callbacks only | ❌ | ❌ |
182
- | Permission gating before sensitive ops | ✅ `AuthGuardian` | ❌ | ❌ | ❌ |
183
- | Tamper-evident audit trail | ✅ HMAC-signed | ❌ | ❌ | ❌ |
184
- | Encryption at rest | ✅ AES-256-GCM | ❌ | ❌ | ❌ |
187
+ | Cross-framework agents in one swarm | ✅ 12 built-in adapters | ⚠️ Nodes can call any code; no adapter abstraction | ⚠️ Extensible via tools; CrewAI-native agents only | ⚠️ Extensible via plugins; AutoGen-native agents only |
188
+ | Atomic shared state (conflict-safe) | ✅ `propose → validate → commit` mutex | ⚠️ State passed between nodes; last-write-wins | ⚠️ Shared memory available; no conflict resolution | ⚠️ Shared context available; no conflict resolution |
189
+ | Hard token ceiling per agent | ✅ `FederatedBudget` (first-class API) | ⚠️ Via callbacks / custom middleware | ⚠️ Via callbacks / custom middleware | ⚠️ Built-in token tracking in v0.4+; no swarm-level ceiling |
190
+ | Permission gating before sensitive ops | ✅ `AuthGuardian` (built-in) | ⚠️ Possible via custom node logic | ⚠️ Possible via custom tools | ⚠️ Possible via custom middleware |
191
+ | Append-only audit log | ✅ plain JSONL (`data/audit_log.jsonl`) | ⚠️ Not built-in | ⚠️ Not built-in | ⚠️ Not built-in |
192
+ | Encryption at rest | ✅ AES-256-GCM (TypeScript layer) | ⚠️ Not built-in | ⚠️ Not built-in | ⚠️ Not built-in |
185
193
  | Language | TypeScript / Node.js | Python | Python | Python |
186
194
 
187
195
  ---
@@ -249,8 +257,8 @@ npm run test:priority # Priority & preemption
249
257
  MIT License — [LICENSE](LICENSE)  ·  [CHANGELOG](CHANGELOG.md)  ·  [CONTRIBUTING](CONTRIBUTING.md)  ·  [![RSS](https://img.shields.io/badge/RSS-releases-orange?logo=rss)](https://github.com/jovanSAPFIONEER/Network-AI/releases.atom)
250
258
 
251
259
  <details>
252
- <summary>Keywords (for search)</summary>
260
+ <summary>Keywords</summary>
253
261
 
254
- ai-agents, agentic-ai, multi-agent, multi-agent-systems, multi-agent-system, agent-framework, ai-agent-framework, agentic-framework, agentic-workflow, llm, llm-agents, llm-agent, large-language-models, generative-ai, genai, orchestration, ai-orchestration, swarm, swarm-intelligence, autonomous-agents, agents, ai, typescript, nodejs, mcp, model-context-protocol, a2a, agent-to-agent, function-calling, tool-integration, context-engineering, rag, ai-safety, multi-agents-collaboration, multi-agents, aiagents, aiagentframework, plug-and-play, adapter-registry, blackboard-pattern, agent-coordination, agent-handoffs, token-permissions, budget-tracking, cost-awareness, atomic-commits, hallucination-detection, content-quality-gate, behavioral-control-plane, governance-layer, compliance-enforcement, fan-out-fan-in, agent-observability, permission-gating, audit-trail, OpenClaw, ClawHub, clawhub, AgentSkills, LangChain adapter, LangGraph, AutoGen adapter, AG2, CrewAI adapter, MCP adapter, LlamaIndex adapter, Semantic Kernel adapter, OpenAI Assistants adapter, Haystack adapter, DSPy adapter, Agno adapter, custom-adapter, AES-256 encryption, HMAC tokens, rate limiting, input sanitization, privilege escalation prevention, agentic-rag, deep-research, workflow-orchestration, ai-assistant, ai-tools, developer-tools, open-source
262
+ multi-agent · agent orchestration · AI agents · agentic AI · agentic workflow · TypeScript · Node.js · LangGraph · CrewAI · AutoGen · MCP · model-context-protocol · LlamaIndex · Semantic Kernel · OpenAI Assistants · Haystack · DSPy · Agno · OpenClaw · ClawHub · shared state · blackboard pattern · atomic commits · guardrails · token budgets · permission gating · audit trail · agent coordination · agent handoffs · governance · cost-awareness
255
263
 
256
264
  </details>
package/dist/index.d.ts CHANGED
@@ -7,7 +7,7 @@
7
7
  * OpenClaw skill interface is implemented for backward compatibility.
8
8
  *
9
9
  * @module SwarmOrchestrator
10
- * @version 4.0.16
10
+ * @version 4.0.17
11
11
  * @license MIT
12
12
  */
13
13
  import { AdapterRegistry } from './adapters/adapter-registry';
package/dist/index.js CHANGED
@@ -8,7 +8,7 @@
8
8
  * OpenClaw skill interface is implemented for backward compatibility.
9
9
  *
10
10
  * @module SwarmOrchestrator
11
- * @version 4.0.16
11
+ * @version 4.0.17
12
12
  * @license MIT
13
13
  */
14
14
  Object.defineProperty(exports, "__esModule", { value: true });
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "network-ai",
3
- "version": "4.0.16",
3
+ "version": "4.0.17",
4
4
  "description": "AI agent orchestration framework for TypeScript/Node.js - plug-and-play multi-agent coordination with 12 frameworks (LangChain, AutoGen, CrewAI, OpenAI Assistants, LlamaIndex, Semantic Kernel, Haystack, DSPy, Agno, MCP, OpenClaw). Built-in security, swarm intelligence, and agentic workflow patterns.",
5
5
  "homepage": "https://github.com/jovanSAPFIONEER/Network-AI#readme",
6
6
  "main": "dist/index.js",