Network Ai

Name: Network Ai
Author: jovanSAPFIONEER

@jovanSAPFIONEER

About Network Ai

Multi-agent orchestration MCP server with atomic shared blackboard, FSM governance, per-agent budget enforcement, and adapters for 12 AI frameworks including LangChain, AutoGen, CrewAI, and OpenAI Assistants.

#multi-agent #orchestration #blackboard #langchain #autogen

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "network-ai": {
      "command": "npx",
      "args": [
        "-y",
        "network-ai-server",
        "--port",
        "3001"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Network Ai?

Network Ai is a multi-agent orchestration framework for TypeScript/Node.js, featuring an atomic shared blackboard, FSM governance, per-agent budget enforcement, and cryptographic audit trails. It integrates with 12 framework adapters (e.g., LangChain, AutoGen, CrewAI) and provides over 20 MCP tools over SSE/JSON-RPC 2.0.

How to use Network Ai?

Run npx network-ai-server --port 3001 to start the MCP server with the built-in tools.

Key features of Network Ai

Atomic shared blackboard prevents race conditions
FSM governance over agent transitions
Per-agent budget enforcement
Cryptographic audit trails
12 framework adapters for orchestration
20+ MCP tools over SSE/JSON-RPC 2.0

Use cases of Network Ai

Build multi-agent systems with race-free shared memory
Govern agent state transitions using finite state machines
Enforce spending limits per agent in orchestrated workflows
Generate cryptographic proofs of agent interactions
Integrate agents across different frameworks (LangChain, AutoGen, etc.)

FAQ from Network Ai

What runtime does Network Ai require?

Node.js with TypeScript support.

How do I start the MCP server?

Run npx network-ai-server --port 3001.

What transports and protocols does it use?

MCP tools are served over SSE and JSON-RPC 2.0.

How many framework adapters are supported?

12 adapters including LangChain, AutoGen, CrewAI, and more.

Does it support cryptographic audit trails?

Yes, it provides cryptographic audit trails for agent interactions.

Comments

More AI & Agents MCP servers

Hass-MCP

voska

Control and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.

307

1Panel

1Panel-dev

🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.

36.1K

欢迎来到智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797