
agent-intercom
io.github.iambasharPublished by GitHub account iambasharv0.2.5Updated Oct 26, 2026
Lets Claude Code, Codex CLI and Antigravity message each other, with live push into open sessions.
Overview
Local mailbox that lets coding agents such as Claude Code, Codex CLI and Antigravity send each other messages, with optional live push into open sessions.
- What you can do
- Send a message into another agent's inbox, optionally with a reply reference
- Read and consume your own messages, or block up to 300 seconds waiting for one
- List the known agents and their mailbox names
- Address a specific session, or route to the most recently active one
- Install, uninstall and inspect the setup across supported CLIs, including a push daemon and a status view
- When to use it
- Useful when you run more than one coding agent on the same machine and want them to hand work to each other, for example asking one agent to review a diff and waiting for its answer, without copying text between terminals.
- Requirements
- Runs as a local process over stdio, installed from the npm package agent-intercom (Node 20 or newer). The install command registers the server with each CLI it finds; live push needs a global install and a background daemon. Set AGENT_NAME for this agent's mailbox name and optionally AGENT_MAIL_DIR to move the mailbox from its default folder. No authentication is declared.
Installation
In SourceWeft
- Open agent-intercom in the dashboard and add it to a workspace.
- 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
[npm] [CI] [License: MIT] [GitHub stars]
[Node 20+] [Zero dependencies] [MCP] [Claude Code] [Codex CLI] [Antigravity]
Let Claude Code, Codex CLI and Antigravity (Gemini) message each other,
and land each message straight in the other agent's open session.
If it saves you time, a ⭐ helps other people find it.
Get started · See it work · How push works · Across machines · CLI · Security · Contributing
[Image] Get started
Using Claude Code only? Install it as a plugin instead:
On Claude Code older than 2.1.275: /plugin marketplace add iambashar/agent-intercom, then /plugin install agent-intercom@agent-intercom. The plugin also adds a skill that teaches Claude the mailbox conventions.
The npx command registers the MCP server with every CLI it finds. Restart them, and each agent gets three tools: mail_send, mail_check and mail_peers. Then ask in plain words:
You → Claude: Ask codex to review the diff in
src/parser.tsand wait for its answer.
Turn on live push so nobody has to poll. Install it globally, because the daemon needs a stable path:
What install changes, per CLI
Use --only claude|codex|gemini for one CLI, and --local to pin a git checkout instead of npx. agent-intercom uninstall removes all of it, including the push daemon.
[!NOTE] The old
geminiCLI no longer accepts personal Google AI Pro sign-ins; Google moved those users to the Antigravity CLI (agy). Its agent is namedgeminihere by default.
[Image] See it work
Neither agent polls. The request appears in Codex as a new turn the moment it is sent, and the reply lands in Claude the same way.
[Image] What you get
[Image] Supported agents
[Image] How push works
-
Delivered once. The daemon renames a message before pushing it, and
mail_checkrenames before reading. Whoever wins the rename delivers it. -
Fails safe. A failed push puts the file back in the inbox and retries after 30 s. If no session is open, the message waits for
mail_check. -
Addressing. Pick a session with
claude.<session-name>,codex.<thread-id-prefix>orgemini.<conversation-prefix>. Otherwise the most recently active session gets it, or the one named in~/.agent-mail/routes.json:
[!WARNING] Push relies on undocumented internals of all three CLIs, and an update can change them without notice. When that happens, pushes fail, get logged, and the mail falls back to the inbox. Protocol details: docs/live-push.md.
Without the push daemon
- Claude Code: docs/claude-monitor.md.
agent-intercom watch claudeunder the Monitor tool wakes the session when mail arrives. - Codex: docs/codex-listen.md. A listener prompt that loops on
mail_check(wait_seconds=300).
[Image] Across machines
Agents on a machine with no shared filesystem, such as a GPU server or an HPC cluster, join over SSH with bridge.sh. It moves each message to the machine its recipient lives on, and pulled mail is pushed like any other.
More: docs/remote-bridge.md.
More than one session per CLI
Names are just AGENT_NAME. Give each session its own, for example claude-api and claude-web:
[Image] CLI
[Image] Security
This is a local mailbox with no authentication. Any process running as you can write to ~/.agent-mail/*/inbox, and an agent treats a message as input to act on. With push on, that input reaches your open sessions without you typing anything.
- Treat inbox contents as untrusted text. Don't let one agent approve destructive actions because a message told it to.
- Pushed messages are labelled
[agent-intercom] message <id> from <sender>. Claude Code also marks them as from another session, not from you. - Push reads tokens only your user can read (
~/.claude/sessions/*.key, the agy session token) and talks only to local sockets. Nothing leaves the machine.
See SECURITY.md to report a problem. Set AGENT_MAIL_DIR to move the mailbox, for example into a project folder.
[Saved you a copy-paste between agents? Star agent-intercom on GitHub]
🤝 Contributing
Contributions are welcome, from a typo fix to support for a new agent.
[Good first issues] [Help wanted] [Discussions]
Read CONTRIBUTING.md before opening a pull request. Everyone here follows the code of conduct.
Develop
Zero runtime dependencies; Node 20+. See CONTRIBUTING.md and the changelog.
MIT licensed · made for people who run more than one coding agent
Source: README.md at commit 610cc64
Tools
0Version history
1- v0.2.5LatestOct 18, 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
