Claude Code Hook Comms (hcom)

hcom - multi-agent communication

[](https://pypi.org/project/hcom/) [](https://opensource.org/licenses/MIT) [](https://www.rust-lang.org/) [](https://github.com/aannoo/hcom/stargazers)

**Let AI agents message, watch, and spawn each other across terminals.**

Agents running in separate terminals are isolated. Context doesn't transfer, decisions get repeated, file edits collide.

Prefix any agent with `hcom` and they're connected. When one agent edits a file, runs a command, or sends a message, other agents can find out immediately.

Works with Claude Code, Gemini CLI, Codex, OpenCode, and any AI tool that can run shell commands.

---

Install

curl -fsSL https://raw.githubusercontent.com/aannoo/hcom/main/install.sh | sh

Or with pip/uv

pip install hcom        # or
uv tool install hcom

---

Quickstart

Run agents with `hcom` in front:

hcom claude
hcom gemini
hcom codex
hcom opencode

Prompt:

send a message to claude

Open the TUI:

hcom

---

How it works

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

---

What you can do

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

What agents can do

Capability	Command
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

...