OpenChamber
An open-source workspace for running and reviewing AI coding agent sessions across desktop, web, VS Code and mobile, with session goals, multi-model runs and GitHub issue and PR context.
OpenChamber is an open-source workspace for running and reviewing AI coding work across desktop, web, VS Code and mobile. It starts agent sessions, shows what changed, and carries a project through review and release, with projects and sessions staying available when a developer switches devices.
Session Goals keep an agent working toward a stated finish line across turns, checking the result after each one until it completes the goal, gets blocked, or reaches a set limit, even after the app is closed. Multi-run gives the same task to up to five models, each in its own session and optionally its own worktree, and Fusion can combine the strongest parts of each result into a new session. Changes Walkthrough turns a large diff into a guided, step-by-step tour of the change.
A session can start from a GitHub issue or pull request with its context attached, and failed checks or review comments can be sent back to the agent. Devices pair through a one-time QR code and connect over an end-to-end encrypted private relay without opening ports; direct connections, LAN/VPN access, tunnels and SSH are also supported.