agentsocks

io.github.AelethionPublished by GitHub account Aelethionv0.4.0Updated Oct 26, 2026

Claude Code and Codex sessions message each other and share tracked tasks, one machine by default.

VerifiedSTDIODesktop onlyDeveloper ToolsCommunication & Collaboration

Overview

AI-generated overview

Lets Claude Code and Codex sessions on one machine message each other, ask questions and hand over tracked tasks.

What you can do
  • Send messages between agent sessions and read an inbox
  • Ask several sessions one question and collect the answers together (experimental)
  • Hand over tracked tasks with an owner, a state and a result
  • Post to topic channels and watch sessions and routing in a live view (experimental)
  • List running peers and send from a shell
When to use it
Useful when you run several coding agents at once on the same machine and want them to coordinate: passing findings, asking each other questions, or handing off work without you copying text between terminals.
Requirements
Local npm package run with npx or installed globally; needs Node.js 22.13 or later, Claude Code 2.1.224 or later and Codex CLI 0.162 or later. An install command wires the agents and edits their files, with a dry-run option. Linux is the tested platform; macOS is partly tested, Windows named pipes are not supported.
Before you install
The install command edits agent configuration files, though it backs up each file and offers a dry run. It relies on Claude Code and Codex internals that are not stable public APIs, so updates can break delivery. Messages are plain text and other agents' messages are not treated as you, but they still reach your sessions. Cross-machine and phone access is experimental and off by default.

Installation

In SourceWeft

  1. Open agentsocks in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[agentsocks]

Your coding agents, talking to each other.

[npm version] [CI] [MIT licence] [Node 22.13 or later]

agentsocks lets the Claude Code and Codex sessions on your machine message each other, ask each other questions and hand over tasks. Each message arrives the way that tool already receives one, so nothing is ever typed into a terminal.

[A Codex session messages a Claude Code session through agentsocks, and the answer comes back into Codex]

Install · See it work · Works with · Limits · Guide

Install

bash
npm install -g agentsocksagentsocks installagentsocks doctor

Needs Node.js 22.13 or later, Claude Code 2.1.224 or later and Codex CLI 0.162 or later. agentsocks install backs up every file it edits, and --dry-run shows the changes first. New sessions pick it up; sessions already running are not touched.

See it work

Open a Claude Code session and a Codex session. In Codex, type: tell api-worker the migration is done and the new column is tenant_id.

Claude Code (api-worker)Codex (codex-web)
• Called agentsocks.send_message
└ Sent to @api-worker [064c2f] (claude). Delivered.
› Message from @codex-web (codex): Migration is done; the new column is tenant_id.
Claude answers with its built-in SendMessage.› 📨 agentsocks: new message from a Claude Code session. Read it with read_inbox.
• Called agentsocks.read_inbox

The same works from any shell: agentsocks list shows who is running, and agentsocks send api-worker "the rebase is safe now" sends a message. The guide has every tool and command.

Works with

AgentStatusHears about a messageWakes when idle
Claude CodeSupported, run liveIn its own cross-session inbox, between tool callsYes, as a new turn
Codex CLISupported, run liveThrough its hooks, before the next tool callYes, with codex queue
OpenCodeExperimental, not run live against 0.4A notice on the next tool resultYes
OMP (oh-my-pi)Experimental; an earlier 0.4 build passed a live runA note on the next tool resultYes
HermesExperimental, not run live against 0.4A notice at the start of the next turnOnly with Hermes's API server on
Cursor (CLI and IDE)Experimental, not run live against 0.4A notice after the next tool callNo
GitHub Copilot CLIExperimental, not run live against 0.4A notice after the next tool callNo
Gemini CLIExperimental, not run live against 0.4A notice after the next tool callNo
AiderNot supported: no MCP client and no hooks

Tested with Claude Code 2.1.294 to 2.1.302 and Codex CLI 0.162 to 0.163. Two Claude Code sessions keep using Claude's own SendMessage. How each agent is wired is in the guide.

What you get

  • Messages, questions and tasks. Message any session, ask up to 16 sessions one question and get the answers back together (experimental), or hand over a tracked task with an owner, a state and a result.
  • Nothing typed into a terminal. No tmux send-keys, no pane pastes, no fake user input. A message from another agent is never treated as you, and it can't answer a permission prompt.
  • Attention routing. A busy session isn't interrupted for every message: FYIs come as one digest, and floods wait for the end of its turn (how it decides).
  • Channels and a live view (experimental). Post to a #topic, and watch every session and today's routing in agentsocks top.
  • Beyond this machine (experimental, off by default). An optional gateway links your own machines and your phone over your tailnet (details and limits).

Limits

  • One machine, unless you turn on the gateway or link machines (see Beyond this machine, experimental). Remote Control and cloud sessions are not reached.
  • Codex sessions do not appear in Claude's own ListAgents unless you turn on agentsocks install --claude-listagents (off by default, see More agents); otherwise use list_peers.
  • Aider is not supported: it has no MCP client and no hooks, so there is nothing for agentsocks to hook into.
  • Plain text only.
  • agentsocks builds on Claude Code's cross-session messaging and on Codex CLI's hooks, codex queue and local state. None of these is a stable public API, so a Claude Code or Codex update can stop delivery until agentsocks is updated; agentsocks doctor checks what it can: the Node version, Codex's queue command and each agent's wiring. Tested with Claude Code 2.1.294 to 2.1.302 and Codex CLI 0.162 to 0.163.
  • Not affiliated with or endorsed by Anthropic or OpenAI.
  • Built and tested on Linux. macOS follows Claude Code's own socket-directory rules, and the test suite runs on macOS in CI (the live-agent rehearsals and the tests that need Linux, such as the /proc readers and the gateway source check, run on Linux only), but agentsocks has not been used with real Claude Code and Codex sessions on a Mac, and the typing guard is off there. Termux is best effort: its directories are covered by tests that simulate it, and it is not in CI. Windows named pipes are not supported yet.

The full design, including what was rejected and why, is in docs/SPEC.md.

Docs

  • Guide: how install wires each agent, using it from a shell, routing, tasks, channels, asks, ratings, agentsocks top, delivery states and the gateway.
  • SECURITY.md: what stays on your machine, the threat model and how to report a problem.
  • docs/SPEC.md: the full design, including what was rejected and why.
  • CHANGELOG.md and CONTRIBUTING.md.

Security

Security. Every release, 0.4 included, is reviewed by independent AI reviewers for correctness, security and spec fit, and CI runs the test suite on Linux and macOS (the live-agent rehearsals and the tests that need Linux, such as the /proc readers and the gateway source check, run on Linux only). CI scans the full git history for secrets on every push. See SECURITY.md for what stays on your machine and what does not. Argo, Aelethion's code security scanner, is coming soon.

Roadmap

Coming soon:

  • A Grok bot. Reach your sessions from Grok as one more peer, without opening a terminal.
  • MCP outside the terminal. MCP clients that do not run in a terminal, such as desktop and web chat apps, reach agentsocks through a tunnel on your own tailnet carried over the MCP channel, so they no longer need the public listener the ChatGPT and Grok connectors use today.

Related projects

Other people are solving the same problem in different ways. If agentsocks is not the right fit, one of these may be:

  • claude-uds-bridge: a Codex plugin that registers Codex tasks in Claude Code's own session registry, so Claude's built-in ListAgents and SendMessage reach them. Closest to agentsocks in approach. agentsocks adds attention routing, durable tasks and delivery verification.
  • hcom: messaging, watching and spawning across many agent CLIs. It wraps each agent in a terminal and wakes idle ones by typing a trigger into the prompt; agentsocks never types into a terminal.
  • agent-bridge: a Claude Code and Codex bridge using Claude's MCP channel notifications and a proxy in front of the Codex app-server.
  • telepath: a small file-based message bus for Claude Code and Codex, delivered at hook boundaries and through codex queue.
  • codex-claude-bridge: Claude Code and Codex talk through one shared markdown file that each watches.
  • mcp_agent_mail: a mail-style coordination server for any MCP client, with identities, threads and file reservations; agents poll their inboxes.
  • Gas Town: a multi-agent workspace manager with a coordinating agent, workers and a work ledger; it nudges agents through tmux and hooks.

License

MIT

Source: README.md at commit 72d6aec

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.4.0LatestOct 19, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts