Mengbi
Quality score 72Cnetwork-ai.org#design#no-code

Network-AI: TypeScript Multi-Agent Orchestration Layer

Network-AI is a TypeScript/Node.js multi-agent orchestration layer with shared-state locking, permission gating, audit trails, FSM governance, and 32 framework adapters. It helps developers coordinate multiple AI agents, enabling cross-agent contradiction detection, task routing, and federated budget enforcement.

Visit website

About this tool

What is Network-AI?

Network-AI is a TypeScript/Node.js multi-agent orchestration layer designed to coordinate multiple AI agents. It provides shared-state locking, permission gating, audit trails, FSM governance, and 32 framework adapters.

Core Capabilities

  • Shared-state coordination: Safely read and write shared data across multiple agents with shared-state locking.
  • Permission gating: Control agent access to tools and resources.
  • Audit trails: Record agent operations with audit logging.
  • FSM governance: Manage agent behavior using finite state machines.
  • Framework adapters: Supports 32 framework adapters, including LlamaIndex and DSPy.
  • MCP server: Registers as a stdio MCP server via .mcp.json.

Use Cases

  • Shared-state coordination for agent swarms
  • Cross-agent contradiction detection
  • Task routing across multiple agent frameworks
  • Federated budget enforcement across LLM agents
  • Multi-agent code review pipeline

Installation Install via npm:

npm install network-ai. The package includes TypeScript library modules and a CLI.

Use cases
  • .mcp.json — registers npx -y -p network-ai network-ai-server --stdio as a stdio MCP server (the -p network-ai selector resolves the binary because the bin name differs from the package name).
  • " } }, { "agentType": "strategy_advisor", "taskPayload": { "instruction": "
  • " metadata: openclaw: emoji: "\U0001F41D" homepage: https://network-ai
  • " npm_full_package: "The npm package (npm install network-ai) adds: TypeScript library modules, CLI (bin/cli
  • " Project Context (Layer 3 — Persistent Memory) Long-lived project state that every agent inherits, regardless of session: # Initialise once python scripts/context_manager
  • " sessions_ops: "platform-provided — outside this skill's control" requires: bins: python3 optional_bins: [] env: {} privacy: audit_log: path: data/audit_log
  • " shell_exec: "optional — AgentRuntime (lib/agent-runtime
  • "Multi-agent code review pipeline", "Federated budget enforcement across 5 LLM agents") Since: version or month you started (e

Features & use cases

.mcp.json — registers npx -y -p network-ai network-ai-server --stdio as a stdio MCP server (the -p network-ai selector resolves the binary because the bin name differs from the package name)." } }, { "agentType": "strategy_advisor", "taskPayload": { "instruction": "" metadata: openclaw: emoji: "\U0001F41D" homepage: https://network-ai" npm_full_package: "The npm package (npm install network-ai) adds: TypeScript library modules, CLI (bin/cli" Project Context (Layer 3 — Persistent Memory) Long-lived project state that every agent inherits, regardless of session: # Initialise once python scripts/context_manager" sessions_ops: "platform-provided — outside this skill's control" requires: bins: python3 optional_bins: [] env: {} privacy: audit_log: path: data/audit_log" shell_exec: "optional — AgentRuntime (lib/agent-runtime"Multi-agent code review pipeline", "Federated budget enforcement across 5 LLM agents") Since: version or month you started (e} async executeAgent( agentId: string, payload: AgentPayload, context: AgentContext ): Promise<AgentResult> { this}, "agent": "data_analyst"} ### cache:revenue_summary {"q4_total": 1250000, "growth": 0// Create a simple agent const adapter = new CustomAdapter()// Detect cross-agent contradictions const contradictions = qa

Sources

Every profile keeps its sources and latest verification date.
01https://network-ai.org/blog/network-ai-v5-15-4

Similar tools

Modelence
modelence.com
88

Modelence is a no-code/low-code platform for AI builders, startups, and product teams to build and ship AI-powered web applications with built-in admin, authentication, and data management.

Freemium · $9+/mo

Open details
T
Threadplane
threadplane.ai
85

Threadplane is an open-source tool for Angular developers to build chat interfaces for AI agents, with streaming, tool calls, and agent-built UI.

Free

Open details
Cossistant
cossistant.com
92

Cossistant is an open-source, code-first AI and human support framework for React and Next.js apps. It lets SaaS teams, developers, and startups add a support chat widget in under 10 lines of code, with programmable actions, custom UI, and integrations with Discord, Stripe, GitHub, and Linear.

Paid · $20+/mo

Open details
Manufact
manufact.com
92

Manufact is a platform for AI engineers and developers to build, deploy, and monitor MCP servers and apps. It offers analytics, managed OAuth, and automatic traffic capture to help teams ship MCP integrations faster.

Freemium · $2+/mo

Open details