by aannoo
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Gemini CLI, Codex, OpenCode
# Add to your Claude Code skills
git clone https://github.com/aannoo/hcomAgents running in separate terminals are isolated from each other. Context doesn't transfer, decisions get repeated, file edits collide.
hcom connects your existing AI tools. When one agent edits a file, runs a command, or sends a message, other agents find out immediately.

curl -fsSL https://raw.githubusercontent.com/aannoo/hcom/main/install.sh | sh
<details><summary>Or with pip/uv</summary>
pip install hcom # or
uv tool install hcom
</details>
Run agents with hcom in front:
hcom claude
hcom gemini
hcom codex
hcom opencode
Prompt:
send a message to claude
Open the TUI:
hcom
Messages arrive mid-turn or wake idle agents immediately.
If 2 agents edit the same file within 30 seconds, both get collision notifications.
Refer to agents by name, tool, terminal, branch, cwd, or set a custom tag.
# hooks record activity and deliver messages
agent → hooks → db → hooks → other agent
<details><summary>What agents can do</summary>
</details>
No comments yet. Be the first to share your thoughts!
Tell any agent:
when codex goes idle send it the next task
watch gemini's file edits, review each and send feedback if any bugs
fork yourself to investigate the bug and report back
find which agent worked on terminal_id code, resume them and ask why it sucks
| | |
|---|---|
| Message each other (intents, threads, broadcast, @mentions) | hcom send |
| Read each other's transcripts (ranges and detail levels) | hcom transcript |
| View terminal screens, inject text/enter for approvals | hcom term |
| Query event history (file edits, commands, status, lifecycle) | hcom events |
| Subscribe and react to each other's activity | hcom events sub |
| Spawn, fork, resume agents in new terminal panes | hcom N claude\|gemini\|codex\|opencode, hcom r, hcom f |
| Kill agents and close their terminal panes/sessions | hcom kill |
| Build context bundles (files, transcript, events) for handoffs | hcom bundle |
Included workflow scripts.
hcom run confess - An agent (or background clone) writes an honesty self-eval. A spawned calibrator reads the target's transcript independently. A judge compares both reports and sends back a verdict via hcom message.
hcom run debate - A judge spawns and sets up a debate with existing agents. It coordinates rounds in a shared thread where all agents see each other's arguments, with shar...