Cc-connect – Remote control Claude Code from your favorite chat app
Multi-platform bridge for Claude Code via chat, but only Claude fully working.
Gives CLI coding agents screen control to test UIs like a human would.
Developers using CLI coding agents
OpenAI Computer Use · Browser Use · Anthropic Computer Use
You install it as a normal CLI tool and can opt to install skills for it on Claude Code, Codex and OpenCode.
It gives agents human-like control of devices. When the agent instructs it to click a button there's a screenshot + coordinate based computer use loop. No DOM or accessibility is used.
I built it because I wanted agents to test things the way a human would, watching the screen and using it from a user perspective.
Would love feedback on onboarding, real use cases, and whether this fits naturally into existing agent workflows.
Multi-platform bridge for Claude Code via chat, but only Claude fully working.
Git for agent reasoning state solves the multi-agent coordination collision problem.
Lets agents actually see the screen and act on it by returning OCR text with pixel coordinates and offering commands like click_at, type_text, and press_key. You can run it instantly with npx (it auto-creates a Python venv and hooks into Apple Vision/Quartz), and there are ready-made integration snippets for Claude, VS Code, and Cursor — a pragmatic, technically neat tool for closed-loop agent UI work. It’s limited to macOS 13+ and Apple APIs, but within that niche it removes a lot of friction.
Voice-controlled agent orchestration across devices when Cursor and Continue only do desktop.
Discord-to-OpenCode bridge with 1000+ weekly npm downloads, but it's a thin wrapper around OpenCode CLI.
Structured JSON beats screenshot soup for agents hitting real websites.