Hcom enables real-time messaging and context sharing between AI coding agents like Claude Code, Gemini CLI, and Codex. Operations teams use it to automate code generation, debugging, and collaboration. It connects to Python-based workflows and integrates with terminal-based development environments.
git clone https://github.com/aannoo/hcom.gitHcom enables real-time messaging and context sharing between AI coding agents like Claude Code, Gemini CLI, and Codex. Operations teams use it to automate code generation, debugging, and collaboration. It connects to Python-based workflows and integrates with terminal-based development environments.
["Set up hcom in your terminal: `pip install hcom && hcom init`","Create a coordination script (e.g., `coordinator.py`) that defines your agent roles and tasks using hcom's Python SDK","Start the workflow: `python coordinator.py --task \"[YOUR_TASK]\" --agents \"claude,gpt4,gemini\"`","Monitor real-time progress in your terminal via hcom's live feed. Use `/debug` to trigger agent collaboration on specific issues","Collect final outputs from the designated output directory. Use `hcom export --format json` for structured results"]
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/aannoo/hcomCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Use hcom to coordinate a multi-agent AI workflow for [TASK]. Have Agent 1 (Claude Code) generate a [FILE_TYPE] file with [FUNCTIONALITY]. Agent 2 (Gemini CLI) will review the file for [CHECK_POINTS]. Agent 3 (Codex) will execute unit tests and suggest fixes. Share real-time context via hcom to resolve any issues. Final deliverable should be [OUTPUT_FORMAT].
## Multi-Agent AI Workflow Execution Report
**Workflow:** Automated REST API endpoint generation with validation and testing
**Agent 1 (Claude Code):** Generated `api_endpoint.py` containing:
```python
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
app = FastAPI()
class User(BaseModel):
name: str
email: str
@app.post("/users/")
async def create_user(user: User):
# Simulated database operation
if user.email.endswith(".invalid"):
raise HTTPException(status_code=400, detail="Invalid email domain")
return {"status": "created", "user_id": 12345}
```
**Agent 2 (Gemini CLI):** Reviewed file for:
- Pydantic model validation (✓)
- FastAPI endpoint structure (✓)
- Error handling implementation (✓)
- Security considerations (⚠️) - Missing rate limiting
**Agent 3 (Codex):** Executed tests via `pytest`:
```
test_api_endpoint.py::test_create_user_valid PASSED
[100%]
test_api_endpoint.py::test_create_user_invalid_email PASSED
[100%]
```
**Real-time Context Sharing via hcom:**
- Agent 1 shared file generation logs showing 3.2s execution time
- Agent 2 pushed security review notes directly to Agent 1's terminal
- Agent 3's test results triggered Agent 1 to add rate limiting middleware
**Final Deliverable:** `api_endpoint.py` with enhanced security and test coverage (98% line coverage). Ready for deployment to staging environment.Google's multimodal AI model and assistant
AI assistant built for thoughtful, nuanced conversation
IronCalc is a spreadsheet engine and ecosystem
Customer feedback management made simple
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan