openchamber

Agentic Development Environment based on OpenCode AI agent

What is openchamber?

Agentic Development Environment based on OpenCode AI agent

Overview of openchamber

What it is

\n\nOpenChamber is an open-source workspace for running and reviewing AI coding work. It is based on the OpenCode AI agent. It can be used on desktop, web, VS Code, and mobile. Projects and sessions remain available across devices.\n\n

Key features

\n\n

  • Session Goals: Give a session a finish line; OpenChamber checks results after each turn and keeps the agent working until the goal is completed, blocked, or a limit is reached. It can continue after closing the app.\n
  • Multi-run and Fusion: Give the same task to up to five models, each in its own session and optionally its own worktree. Compare results or combine the strongest parts into a new session using Fusion.\n
  • Changes Walkthrough: Turns a large diff into an AI-guided tour, grouping related edits into steps and explaining how pieces fit together.\n
  • Preview: Open an app beside the conversation; point at an element to send the agent its screenshot, styles, position, and browser errors. The desktop app can do the same with any web page in its built-in browser.\n
  • GitHub integration: Start a session from a GitHub issue or pull request with context attached. Send failed checks or review comments back to the agent, then update or merge the pull request from OpenChamber.\n
  • Cross-device continuity: Open the same projects and sessions from Desktop, Web/PWA, VS Code, iOS, or Android. Check progress, answer questions, review changes, and reattach to a running terminal.\n
  • Private remote access: Pair a device with a one-time QR code and connect through Private Relay with end-to-end encryption, without opening ports or exposing a public server. Direct connections, LAN/VPN, Cloudflare/Ngrok tunnels, and SSH are also supported.\n\n

Use cases

\n\n

  • Running AI coding agents with defined goals and reviewing their output.\n
  • Comparing multiple model runs on the same task and selecting or combining the best results.\n
  • Reviewing large code changes through guided walkthroughs.\n
  • Inspecting a running application and providing visual context to the agent.\n
  • Managing GitHub workflows from issue to pull request within the workspace.\n
  • Continuing work across different devices, including mobile.\n
  • Scheduling recurring coding tasks.\n\n

Getting started

\n\nDesktop: Download the latest release from GitHub Releases. Desktop bundles the matching OpenCode CLI. Linux packages: .deb (Debian, Ubuntu), .rpm (Fedora, openSUSE), and AppImage.\n\nbash\nsudo apt install ./OpenChamber-*-linux-amd64.deb # Debian, Ubuntu\nsudo dnf install ./OpenChamber-*-linux-x86_64.rpm # Fedora\nchmod +x OpenChamber-*.AppImage\n./OpenChamber-*.AppImage\n\n\nVS Code: Install OpenChamber from the Visual Studio Marketplace.\n\niOS and Android: Join the iOS beta on TestFlight. For Android, download the .apk from the Canary release.\n\nCLI for Web and PWA: Requires Node.js 24.14+. CLI/Web and VS Code use your installed OpenCode CLI.\n\nbash\ncurl -fsSL https://raw.githubusercontent.com/openchamber/openchamber/main/scripts/install.sh | bash\nopenchamber --ui-password be-creative-here\n\n\n

License and pricing

\n\nMIT license. Open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/openchamberopenchamber.svg)](https://yunodb.com/tools/openchamberopenchamber?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/openchamberopenchamber?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/openchamberopenchamber.svg" alt="Featured on YunoDB" height="20"></a>