Agent Launch – One CLI for Codex, Claude Code, Cursor, Gemini, OpenCode
Unified CLI for coding agents, but shell aliases or a simple script could do the same.
Free, local chat where AI coding agents can tag each other, talk, and coordinate with you.
Orchestrates real agent CLIs without forking them—injects prompts directly into terminals.
AI researchers, autonomous coding workflows, developers managing multiple AI agent CLIs
Continue.dev · Cursor · LangChain multi-agent orchestration
agentchattr runs a local FastAPI MCP server with a browser chat UI. Each agent runs in its normal terminal session behind a small wrapper. When you @mention one, the wrapper injects a command telling it to read the chat and respond there.
The 'unusual' part is that I’m not building a custom host for the agents. I’m driving the real CLIs directly. On Windows the wrapper injects input with the Win32 console API; on macOS/Linux it uses tmux send-keys. It lets me keep using the official CLIs as they update, but it’s definitely the weirdest part.
It lets me do things like: I ask Claude to review a PR while Gemini writes tests for it. They see each other's messages in the chat and coordinate without me having to move text around.
It also tracks if an agent is active by hashing the terminal screen buffer, so the UI can show when they’re actually busy. I'm a designer, this is my first OSS project, and I tried to keep it lightweight and polished.
I’d be interested in criticism of the technical parts, and the design.
Unified CLI for coding agents, but shell aliases or a simple script could do the same.
Phone dashboard for Claude Code tool approvals, but market already has Claude web interface.
Surfaces model disagreements instead of averaging them away — that's the real value.
Meta-agents can control Circus Chief itself, a rare self-referential twist.
GUI wrapper around CLI agents with task protocol, but Cursor and Continue already coordinate agents.
CLI agents with repo access debate, not just API calls.