# Agent Peers

> Use this tool when you need to enable seamless communication between multiple Claude Code or Codex CLI sessions on the same machine. Agent Peers solves the problem of session isolation by providing peer-to-peer messaging infrastructure, allowing for efficient task summary updates and message exchange. It takes in CLI sessions as input and outputs synchronized task updates and messages, ideal for use cases requiring coordinated workflow management.

Canonical page: https://skillsregistry.net/skills/co-messi-agent-peers  
JSON: https://api.skillsregistry.net/v1/skills/co-messi-agent-peers

## Description

Agent Peers provides peer-to-peer messaging infrastructure for multiple Claude Code or Codex CLI sessions running on the same machine. It uses a local SQLite broker on port 7900 with no cloud or external API dependencies. Tools include peer discovery with machine/directory/repo scoping, message sending and retrieval, task summary updates, and session renaming. Built with TypeScript and Bun.

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/co-messi-agent-peers)
- **Repository:** <https://github.com/co-messi/agent-peers-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "co-messi-agent-peers"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/co-messi-agent-peers` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/co-messi-agent-peers/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt