Hcom

hcom

Connect independent coding agents across terminals and machines. They can message each other, monitor activity, react to events, and launch more agents. Start an agent  with hcom in front, then prompt normally.

Use it to coordinate multi-agent pipelines, run different AI CLIs as each other's subagents, or just to avoid copy-pasting.

Works with claude codex opencode grok hermes pi omp agy copilot qoder cursor kimi kilo gemini

https://github.com/user-attachments/assets/1ce23ed9-f529-4be0-8124-816aa4c2fd43

Install

macOS, Linux, Windows:

or: brew install aannoo/hcom/hcom

or install script

macOS, Linux, Android:

Windows:

Quickstart

Terminal 1:

Terminal 2:

Prompt:

ask the other agent their favorite cake

- review what claude did and send it fixes

- spawn 3x opencode, split work, collect results

- fork yourself to investigate the bug and report back

- when codex goes idle, send it the next task

- find the agent that worked on that feature, resume it and ask it why it's bad

Open the TUI dashboard:

What agents can do

- Message each other in real time. Messages arrive mid-turn (after tool calls) or wake idle agents immediately.

- Observe who's running and what they're doing: status, transcripts, tool results, file edits, commands, live terminal screens, context/token usage. Search past conversations.

- Subscribe to status changes, commands, file edits, collisions, and session events, then react automatically.

- Control: spawn, fork, resume, kill agents in any terminal emulator or headless.

How it works

Hooks record activity to a local SQLite database and deliver messages from it.

Hooks activate only when an agent is launched with hcom in front. Normal usage is unaffected.

Any other AI tool without hooks can join by running hcom start

In any CLI…