network-ai 4.0.8 → 4.0.9

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 CHANGED
@@ -1,35 +1,43 @@
1
- # Network-AI: Multi-Agent Orchestration Framework
1
+ # Network-AI
2
2
 
3
- **The plug-and-play AI agent orchestrator for TypeScript/Node.js -- connect 12 agent frameworks with zero glue code**
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-v4.0.8-blue.svg)](https://github.com/jovanSAPFIONEER/Network-AI/releases)
7
+ [![Release](https://img.shields.io/badge/release-v4.0.9-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
- [![ClawHub](https://img.shields.io/badge/ClawHub-network--ai-orange.svg)](https://clawhub.ai/skills/network-ai)
10
- [![Node.js](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg)](https://nodejs.org)
11
- [![TypeScript](https://img.shields.io/badge/TypeScript-5.x-3178C6.svg)](https://typescriptlang.org)
12
- [![Python](https://img.shields.io/badge/python-3.9+-green.svg)](https://python.org)
13
- [![License](https://img.shields.io/badge/license-MIT-brightgreen.svg)](LICENSE)
14
- [![Socket](https://socket.dev/api/badge/npm/package/network-ai)](https://socket.dev/npm/package/network-ai/overview)
15
- [![AgentSkills](https://img.shields.io/badge/AgentSkills-compatible-orange.svg)](https://agentskills.io)
16
9
  [![Tests](https://img.shields.io/badge/tests-1216%20passing-brightgreen.svg)](#testing)
17
10
  [![Adapters](https://img.shields.io/badge/frameworks-12%20supported-blueviolet.svg)](#adapter-system)
18
- [![RSS Feed](https://img.shields.io/badge/RSS-releases-orange?logo=rss)](https://github.com/jovanSAPFIONEER/Network-AI/releases.atom)
11
+ [![License](https://img.shields.io/badge/license-MIT-brightgreen.svg)](LICENSE)
12
+ [![Socket](https://socket.dev/api/badge/npm/package/network-ai)](https://socket.dev/npm/package/network-ai/overview)
13
+ [![Node.js](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg)](https://nodejs.org)
14
+ [![TypeScript](https://img.shields.io/badge/TypeScript-5.x-3178C6.svg)](https://typescriptlang.org)
15
+ [![ClawHub](https://img.shields.io/badge/ClawHub-network--ai-orange.svg)](https://clawhub.ai/skills/network-ai)
19
16
  [![Integration Guide](https://img.shields.io/badge/docs-integration%20guide-informational.svg)](INTEGRATION_GUIDE.md)
20
17
 
21
- > **Legacy Users:** This skill works with **Clawdbot** and **Moltbot** (now OpenClaw). If you're searching for *Moltbot Security*, *Clawdbot Swarm*, or *Moltbot multi-agent* -- you're in the right place!
18
+ Network-AI is a TypeScript/Node.js multi-agent orchestrator for teams that need shared state, guardrails, budgets, and cross-framework coordination.
19
+
20
+ - **Shared blackboard with locking** — atomic commits prevent race conditions and split-brain failures across parallel agents
21
+ - **Guardrails and budgets** — FSM governance, per-agent token ceilings, HMAC audit trails, and permission gating
22
+ - **12 framework adapters** — LangChain, AutoGen, CrewAI, OpenAI Assistants, LlamaIndex, Semantic Kernel, and more in one orchestrator — no glue code, no lock-in
23
+
24
+ If network-ai saves you time, a ⭐ helps others find it.  |  [**60-second quickstart →**](#hello-world----get-running-in-60-seconds)  |  [**Architecture →**](#architecture)  |  [**All adapters →**](#adapter-system)
25
+
26
+ ---
27
+
28
+ ## Why teams use Network-AI
22
29
 
23
- If network-ai saves you time, a on GitHub helps others find it.
30
+ | Problem | How Network-AI solves it |
31
+ |---|---|
32
+ | Race conditions in parallel agents | Atomic blackboard: `propose → validate → commit` with file-system mutex |
33
+ | Agent overspend / runaway costs | `FederatedBudget` — hard per-agent token ceilings with live spend tracking |
34
+ | No visibility into what agents did | HMAC-signed audit log on every write, permission grant, and FSM transition |
35
+ | Locked into one AI framework | 12 adapters — mix LangChain + AutoGen + CrewAI + custom in one swarm |
36
+ | Agents escalating beyond their scope | `AuthGuardian` — scoped permission tokens required before sensitive operations |
24
37
 
25
- Connect agents across **12 frameworks** through a shared blackboard with built-in security, compliance enforcement, and behavioral governance -- in a single `npm install`. No glue code, no lock-in.
38
+ > Validated by **1,216 passing tests** across 9 test suites [see testing section](#testing)
26
39
 
27
- **Why Network-AI?**
28
- - **Framework-agnostic** -- LangChain, AutoGen, CrewAI, MCP, OpenAI Assistants, and 7 more in one orchestrator
29
- - **Governed coordination** -- FSM-controlled agent turns, permission gating, audit trails, budget ceilings
30
- - **Shared state** -- Atomic blackboard with conflict resolution for safe parallel agent coordination
31
- - **Production security** -- AES-256 encryption, HMAC audit logs, rate limiting, input sanitization
32
- - **Zero config** -- Works out of the box with `createSwarmOrchestrator()`
40
+ ---
33
41
 
34
42
  ## Architecture
35
43
 
package/bin/mcp-server.ts CHANGED
@@ -29,7 +29,7 @@
29
29
  * http://localhost:3001/tools (list all tools)
30
30
  *
31
31
  * @module bin/mcp-server
32
- * @version 4.0.8
32
+ * @version 4.0.9
33
33
  */
34
34
 
35
35
  import {
@@ -103,7 +103,7 @@ function parseArgs(argv: string[]): ServerArgs {
103
103
 
104
104
  function printHelp(): void {
105
105
  console.log(`
106
- network-ai-server — Network-AI MCP Server v4.0.8
106
+ network-ai-server — Network-AI MCP Server v4.0.9
107
107
 
108
108
  Usage: npx ts-node bin/mcp-server.ts [options]
109
109
 
@@ -140,7 +140,7 @@ async function main(): Promise<void> {
140
140
  process.exit(0);
141
141
  }
142
142
 
143
- console.log(`\n[network-ai-server] Starting MCP Server v4.0.8`);
143
+ console.log(`\n[network-ai-server] Starting MCP Server v4.0.9`);
144
144
  console.log(`[network-ai-server] Board: ${args.board} | Port: ${args.port}`);
145
145
 
146
146
  // --------------------------------------------------------------------------
@@ -29,7 +29,7 @@
29
29
  * http://localhost:3001/tools (list all tools)
30
30
  *
31
31
  * @module bin/mcp-server
32
- * @version 4.0.8
32
+ * @version 4.0.9
33
33
  */
34
34
  export {};
35
35
  //# sourceMappingURL=mcp-server.d.ts.map
@@ -30,7 +30,7 @@
30
30
  * http://localhost:3001/tools (list all tools)
31
31
  *
32
32
  * @module bin/mcp-server
33
- * @version 4.0.8
33
+ * @version 4.0.9
34
34
  */
35
35
  Object.defineProperty(exports, "__esModule", { value: true });
36
36
  const index_1 = require("../index");
@@ -102,7 +102,7 @@ function parseArgs(argv) {
102
102
  }
103
103
  function printHelp() {
104
104
  console.log(`
105
- network-ai-server — Network-AI MCP Server v4.0.8
105
+ network-ai-server — Network-AI MCP Server v4.0.9
106
106
 
107
107
  Usage: npx ts-node bin/mcp-server.ts [options]
108
108
 
@@ -135,7 +135,7 @@ async function main() {
135
135
  printHelp();
136
136
  process.exit(0);
137
137
  }
138
- console.log(`\n[network-ai-server] Starting MCP Server v4.0.8`);
138
+ console.log(`\n[network-ai-server] Starting MCP Server v4.0.9`);
139
139
  console.log(`[network-ai-server] Board: ${args.board} | Port: ${args.port}`);
140
140
  // --------------------------------------------------------------------------
141
141
  // 1. Create orchestrator + blackboard
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 4.0.8
10
+ * @version 4.0.9
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 4.0.8
11
+ * @version 4.0.9
12
12
  * @license MIT
13
13
  */
14
14
  Object.defineProperty(exports, "__esModule", { value: true });
@@ -125,7 +125,7 @@ class McpCombinedBridge {
125
125
  return this._ok(id, {
126
126
  protocolVersion: '2024-11-05',
127
127
  capabilities: { tools: {} },
128
- serverInfo: { name: this.name ?? 'network-ai', version: '4.0.7' },
128
+ serverInfo: { name: this.name ?? 'network-ai', version: '4.0.9' },
129
129
  });
130
130
  // Client signals it's ready — notification (no response needed, but
131
131
  // some clients send it as a request with an id)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "network-ai",
3
- "version": "4.0.8",
3
+ "version": "4.0.9",
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",