Network Ai
@jovanSAPFIONEER
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.
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.
