aannoo avatar

Hcom Agent Messaging

This connects AI coding agents running in separate terminals so they can message each other, watch file edits, and spawn new agents in real time. You'd use it when you want Claude in one terminal to hand off context to Gemini in another, or have a reviewer agent automatically check another agent's work and send feedback. The hook system is automatic for Claude, Gemini, Codex, and others. Setup is straightforward but watch out for the gotchas around threading and cleanup, especially if you're writing multi-agent scripts. The reference patterns are actually helpful. It's solving a real coordination problem if you're running multiple agents, though you'll spend some time learning the event system and intent flags.

GitHub stars
337
last updated
Jun 10, 2026

Install

$ npx -y skills add aannoo/hcom --skill hcom-agent-messaging --agent claude-code

Installs into .claude/skills of the current project.

Files

hcom — multi-agent communication for AI coding tools

AI agents running in separate terminals are isolated. hcom connects them via hooks and a shared database so they can message, watch, and spawn each other in real-time.

Start an agent with hcom in front, then prompt normally.

Use hcom to:

  • coordinate multi-agent pipelines
  • run different AI CLIs as each other's subagents
  • avoid copy-pasting
uv tool install hcom
hcom claude       # or: hcom gemini, hcom codex, hcom opencode, hcom kilo, hcom pi, hcom omp, hcom agy, hcom cursor, hcom kimi, hcom copilot, hcom qoder, hcom grok, hcom hermes
hcom              # TUI dashboard

Quickstart:

# terminal 1
hcom claude

# terminal 2
hcom codex

Prompt normally — e.g. review what claude did and send it fixes


what humans can do

tell any agent:

send a message to claude

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

Sponsors

Details

Repository
github.com/aannoo/hcom
Category
AI & Agent Building
License
MIT
First seen
Jun 11, 2026
1agentworkforce avatarusing-agent-relayagentworkforce/relayOnce you're inside an Agent Relay workspace as a registered participant or spawned worker, this is your operational playbook.0skills.sh installs
2anthropics avatarMCP Integrationanthropics/claude-codeThis skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", 0skills.sh installs
3ar9av avataragent-research-aggregatorar9av/paperorchestraPre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any user-specified directory for experimentation lo0skills.sh installs
4ar9av avatarcontent-refinement-agentar9av/paperorchestraStep 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with st0skills.sh installs
5ar9av avatarliterature-review-agentar9av/paperorchestraStep 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, v0skills.sh installs
6ar9av avatarplotting-agentar9av/paperorchestraStep 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimen0skills.sh installs