Skip to main content
Glama

Placet (Latin, "it pleases"): the formal word for giving your consent. Nothing crosses from one agent to another without it.


Why

If you run Claude Code, Codex and Antigravity side by side, you know the problems:

  • You are tied to the desk. An agent stops to ask "may I run the migration?" and waits until you are back.

  • The agents cannot talk to each other. You copy a plan from Claude into Codex for a review, then paste the review back.

  • When they can talk, nobody is watching. Letting agents prompt each other unsupervised is how loops and surprises happen.

Placet sits between your agents and your phone. Every session registers itself; you read its conversation, answer its questions and write to it from anywhere. When one agent wants another to do something, the request comes to you first: approve it, edit the prompt, or reject it.

Related MCP server: agentchan

Features

  • One inbox for all your agents. Questions from Claude, Codex and Antigravity arrive as push notifications (via ntfy) and as cards in a PWA you add to your home screen.

  • Read and write to any session. The conversation as you see it on the PC: Markdown, highlighted code, tool calls collapsed into one line. Write a message and it wakes the session, as if you had typed it at the desk.

  • An approval bus between agents. placet_send_to_agent lets an agent ask another one for a review, a test run or a second opinion. You approve, edit or reject; the answer goes back to the session that asked.

  • Attachments both ways. Images you pasted in the desktop apps, pictures an agent generated, PDFs it shared with placet_share_file, and photos or files you attach from the phone.

  • Reliable by design. Hooks write to a local queue and never block a turn. Each request tracks delivery, execution and reply separately; an uncertain delivery is never re-sent behind your back. One request at a time per session, and time alone never frees the queue.

  • Adaptive. Two columns on the desktop, a bottom bar on the phone, a theme per provider.

How it works

flowchart LR
    phone["πŸ“± Phone<br/>PWA + ntfy"]
    subgraph pc["Your PC"]
        backend["Placet backend<br/>FastAPI Β· SQLite Β· audit log"]
        bridge["Bridge<br/>runs as you"]
        mcp["Placet MCP tools"]
        subgraph agents["Agent sessions"]
            claude["Claude Code"]
            codex["Codex"]
            agy["Antigravity"]
        end
    end
    phone <-- "Tailscale (HTTPS)" --> backend
    agents -- "hooks β†’ local queue" --> bridge
    agents -- "ask Β· send Β· reply Β· share" --> mcp --> backend
    bridge <-- "jobs, events" --> backend
    bridge -- "wake: waiter Β· codex queue Β· app API" --> agents
  • Backend β€” runs as its own system user, keeps requests and the audit log, and is reachable from your phone only through your Tailscale network. It never stores your conversations.

  • Bridge β€” runs as you: it reads conversations on demand, wakes sessions, forwards hook events from the local queue and checks which projects are excluded.

  • Hooks β€” every Claude Code, Codex and Antigravity session registers itself and reports when a turn starts and ends. Sessions stay quiet until a Placet message arrives; a .placet-off file keeps a project out entirely.

  • MCP tools β€” placet_ask_human, placet_send_to_agent, placet_reply, placet_share_file and friends, available to every agent.

Provider

Registers with

Woken by

Claude Code (desktop app and CLI)

hooks

a background waiter (asyncRewake)

OpenAI Codex (desktop app and CLI)

hooks

codex queue

Google Antigravity 2.0

hooks

the app's language server

Security, briefly

  • Two doors. Agents talk to 127.0.0.1 with their own token; you reach the PWA through a Unix socket exposed with tailscale serve, and only the Tailscale logins you allow get in.

  • Least privilege. The backend has no access to your files. The bridge reads only what a page or an attachment needs, and an attachment is requested by id, never by path.

  • Attachments are checked. Only files the provider adapter recognised, inside the folders the app uses for that conversation (symlinks resolved), and real JPEG, PNG, WebP or PDF content. Shared files are never taken from hidden folders like .ssh.

  • Honest limits. Agents run as your user and could read each other's tokens: tokens identify agents in the audit log, they do not isolate them. Some integrations rely on undocumented app internals and may break on updates; they are isolated in adapters.

More in ARCHITETTURA.md (Italian).

Quick start

Placet targets Linux with Python 3.11+, Node.js 18+, Tailscale and, for push notifications, an ntfy server.

git clone <this repository> placet && cd placet
sudo deploy/install.sh                  # backend service, bridge service, PWA build
python3 /opt/placet/hooks/install.py    # hooks for Claude Code, Codex and Antigravity
sudo tailscale serve --bg unix:/run/placet/human.sock

Then add the Placet MCP server to your agents, approve the Codex hooks once with /hooks, restart the apps, and open https://<your-machine>.<tailnet>.ts.net on your phone.

The complete guide β€” environment variables, notifications, MCP setup, the tmux channel β€” is in docs/INSTALL.it.md (Italian).

Status

Placet is alpha, used every day by its author on one machine. The interface and the design documents are in Italian for now.

  • βœ… Questions and approvals from the phone, push notifications, audit log

  • βœ… Sessions on the phone: read, write, wake (Claude Code, Codex, Antigravity)

  • βœ… Reliability: local event queue, delivery / execution / reply, one request at a time

  • βœ… Attachments: viewing, placet_share_file, uploads from the phone; @ mentions

  • 🚧 "Right now" messages inside a running turn, distinct notifications, waiter health

  • πŸ—ΊοΈ Typed relations between sessions with per-relation policy (manual / automatic), loop limits, a graph editor

  • πŸ—ΊοΈ Usage, context and effort per session; creating sessions from the phone

Design notes: REQUISITI.md (requirements) Β· ARCHITETTURA.md (architecture) Β· LABORATORIO.md (experiments).

Development

python3 -m venv .venv && .venv/bin/pip install -r requirements.txt
.venv/bin/python -m pytest -q                    # backend, bridge, hooks
cd frontend && npm install && npx vitest run     # PWA
.venv/bin/python run_all.py                      # backend + bridge in one process (development only)

Contributing

Issues and pull requests are welcome, especially adapters for other agents and checks on new versions of the supported apps. Please keep the two rules that shape the project: nothing reaches an agent from another agent without passing through Placet's policy, and nothing on the phone reveals a file the user did not choose to share.

License

Licensed under the Apache License 2.0. Copyright 2026 Paolo Pietrelli.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI coding agents to communicate directly with each other across machines, with support for rooms, pairing, and encrypted messaging.
    4 npm
    8
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables coding agents to communicate with each other by sending messages and waiting for replies across sessions, supporting agents like Claude Code, Codex, and Grok.
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI coding agents to coordinate through a local, pull-only message board by registering sessions, posting updates, proposing and accepting tasks, holding leases, and reading or acknowledging updates under scoped human authorization.
    8
    MIT