Ermöglicht es Claude Code und Codex Sessions, sich gegenseitig zu Nachrichten zu senden, Aufgaben zu teilen und die Arbeit ohne Terminal-Eingaben zu koordinieren.
Auch bekannt als Aelethion/agentsocks
- Stars
- 1
- Tools
- —
- Downloads, 30 Tage
- —
- Neueste Version
- 0.4.0
- Letzter Commit
- 26. Okt. 2026
- Lizenz
- MIT
Was ist agentsocks MCP?
Ermöglicht es Claude Code und Codex Sessions, sich gegenseitig zu Nachrichten zu senden, Aufgaben zu teilen und die Arbeit ohne Terminal-Eingaben zu koordinieren.
Zusammenfassung generiert aus dem README des Projekts
Über agentsocks MCP server
agentsocks ermöglicht die Kommunikation zwischen verschiedenen Coding-Agents, die auf deinem lokalen Rechner laufen. Es erlaubt Claude Code und Codex CLI Sessions, Nachrichten auszutauschen, Fragen zu stellen und Aufgaben zu übergeben, ohne dass manuelle Terminal-Eingaben oder gefälschte Tastatureingaben nötig sind. Dieses Tool wurde für Entwickler entwickelt, die mehrere KI-Agents gleichzeitig koordinieren wollen, um komplexe Workflows zu verwalten.
Um es zu nutzen, musst du Node.js 22.13 oder neuer sowie spezifische Versionen von Claude Code und Codex CLI installiert haben. Der Installationsprozess nutzt den agentsocks command, um deine Umgebung zu konfigurieren, und kann mit dem doctor command überprüft werden. Während es primär auf einer einzelnen Maschine läuft, ermöglicht ein experimentelles Gateway-Feature das Verbinden von Geräten über ein Tailnet. Das System nutzt Attention Routing, um sicherzustellen, dass beschäftigte Sessions nicht durch Nachrichtenfluten unterbrochen werden; stattdessen werden Zusammenfassungen geliefert oder gewartet, bis der Agent wieder im Idle-Modus ist.
Was du damit machen kannst
- 1Multi-Agent-Aufgaben koordinierenDu kannst einen Agent anweisen, einen anderen zu benachrichtigen, sobald ein bestimmter technischer Meilenstein erreicht wurde.
- 2Aufgabenübergaben automatisierenEntwickler können verfolgte Aufgaben mit spezifischen Ownern und Ergebnissen an verschiedene Coding-Sessions zuweisen.
- 3Informationen an mehrere Agents broadcastenDu kannst eine einzige Frage an bis zu 16 verschiedene Sessions senden, um kollektive Antworten zu sammeln.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du agentsocks MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenagentsocks MCP in Claude Code installieren
$ claude mcp add agentsocks -- npx -y agentsocksagentsocks MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"agentsocks": {
"command": "npx",
"args": [
"-y",
"agentsocks"
]
}
}
}agentsocks MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"agentsocks": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agentsocks"
]
}
}
}agentsocks MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"agentsocks","type":"stdio","command":"npx","args":["-y","agentsocks"]}'agentsocks MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"agentsocks": {
"command": "npx",
"args": [
"-y",
"agentsocks"
]
}
}
}agentsocks MCP in Codex installieren
$ codex mcp add agentsocks -- npx -y agentsocksagentsocks MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.agentsocks] command = "npx" args = ["-y", "agentsocks"]
agentsocks MCP in Gemini CLI installieren
$ gemini mcp add -s user agentsocks npx -- -y agentsocksagentsocks MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"agentsocks": {
"command": "npx",
"args": [
"-y",
"agentsocks"
]
}
}
}Automatisierte Checks
Geluften am 14. Nov. 2026Vollständiger Bericht →Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren
- Source Repository verknüpft und erreichbaraelethion/agentsocks is public and reachablegithub.com/aelethion/agentsocks ↗Bestanden
- Paket nennt dieses Repository als Quelleagentsocks names aelethion/agentsocks as sourcenpmjs.com/package/agentsocks ↗Bestanden
- Build-Provenienz (Sigstore-Attestierung)Sigstore attestation for agentsocksnpmjs.com/package/agentsocks/v/0.4.0#provenance ↗Bestanden
- Open Source Lizenz (OSI)MITspdx.org/licenses/MIT.html ↗Bestanden
- Commit oder Release im letzten JahrLast commit or release 2026-10-26github.com/aelethion/agentsocks ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNo popular package one edit away from agentsocksBestanden
- Keine kritischen Advisories im Paket oder seinen Abhängigkeiten99 resolved dependencies checked; no critical advisoryosv.dev ↗Bestanden
- Keine versteckten Anweisungen an das Modell0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNicht geprüft
- Remote-Endpoint beantwortet den MCP-HandshakeNicht geprüft
README
Auf GitHub ansehenagentsocks 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.
Install
npm install -g agentsocks
agentsocks install
agentsocks 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
| Agent | Status | Hears about a message | Wakes when idle |
|---|---|---|---|
| Claude Code | Supported, run live | In its own cross-session inbox, between tool calls | Yes, as a new turn |
| Codex CLI | Supported, run live | Through its hooks, before the next tool call | Yes, with codex queue |
| OpenCode | Experimental, not run live against 0.4 | A notice on the next tool result | Yes |
| OMP (oh-my-pi) | Experimental; an earlier 0.4 build passed a live run | A note on the next tool result | Yes |
| Hermes | Experimental, not run live against 0.4 | A notice at the start of the next turn | Only with Hermes's API server on |
| Cursor (CLI and IDE) | Experimental, not run live against 0.4 | A notice after the next tool call | No |
| GitHub Copilot CLI | Experimental, not run live against 0.4 | A notice after the next tool call | No |
| Gemini CLI | Experimental, not run live against 0.4 | A notice after the next tool call | No |
| Aider | Not 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 inagentsocks 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
ListAgentsunless you turn onagentsocks install --claude-listagents(off by default, see More agents); otherwise uselist_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 queueand 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 doctorchecks what it can: the Node version, Codex'squeuecommand 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
/procreaders 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
ListAgentsandSendMessagereach 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
agentsocks MCP Fragen
Wie füge ich agentsocks MCP zu Claude Code hinzu?
Führe claude mcp add agentsocks -- npx -y agentsocks in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich agentsocks MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Erfordert agentsocks das Tippen im Terminal, um zu kommunizieren?
Nein, Nachrichten kommen über bestehende Tool-Channels an, sodass niemals etwas in ein Terminal getippt werden muss.
Was sind die Systemanforderungen für agentsocks?
Es wird Node.js 22.13 oder neuer, Claude Code 2.1.224 oder neuer und Codex CLI 0.162 oder neuer benötigt.