network-ai

A multi-agent coordination layer for Claude Code that lets several AI agents share state, control permissions, track token budgets, and query an audit log.

In plain words
What is it for?
Managing shared proposals and commits, enforcing signed permissions, tracking distributed budgets, and querying append-only activity records through MCP.
Why use it?
It provides shared coordination and records for work performed by multiple agents instead of leaving each agent’s state and actions isolated.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add Jovancoding/Network-AI
agentmods
npx agentmods add plugins/jovancoding/network-ai/marketplace
Clone the repo
git clone --depth 1 https://github.com/Jovancoding/Network-AI

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

network-ai scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude-plugin/marketplace.json · 36 lines

What it actually says

{
  "name": "network-ai",
  "owner": {
    "name": "OpenClaw Community",
    "url": "https://github.com/Jovancoding/Network-AI"
  },
  "metadata": {
    "description": "Network-AI — a multi-agent coordination layer for Claude Code: shared blackboard state, permission gating, federated budgets, and audit queries over MCP.",
    "version": "5.15.1"
  },
  "plugins": [
    {
      "name": "network-ai",
      "source": "./",
      "description": "Gives Claude Code a multi-agent coordination layer over MCP — an atomic shared blackboard (locked propose/validate/commit), permission gating with HMAC/Ed25519-signed tokens, federated token-budget tracking, and append-only audit-log queries. Backed by an orchestrator with 32 framework adapters (LangChain, AutoGen, CrewAI, Gemini, and more).",
      "version": "5.15.1",
      "author": {
        "name": "OpenClaw Community",
        "url": "https://github.com/Jovancoding/Network-AI"
      },
      "homepage": "https://network-ai.org",
      "repository": "https://github.com/Jovancoding/Network-AI",
      "license": "MIT",
      "keywords": [
        "ai-agents",
        "multi-agent",
        "orchestration",
        "mcp",
        "blackboard",
        "swarm"
      ],
      "category": "orchestration"
    }
  ]
}
Files

What ships with it

1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 36 lines scan A 68a7015887ea

Subscribe to this mod's changes

network-ai is a plugin published in the GitHub repository Jovancoding/Network-AI (72 stars, last pushed 7d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.