# openchamber/openchamber

Desktop and web interface for OpenCode AI agent

Repository: https://github.com/openchamber/openchamber
Canonical: https://ross.abutalabs.com/products/openchamber
Homepage: https://openchamber.dev/
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, opencode, agentic-engineering, agents, enginering
Last push: 2026-08-26T22:25:13+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 25
- inputs: {"age_days": 356, "days_push": 7, "days_rel": 7, "gap_med": 1.0, "n_releases_24m": 137}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9270, forks 975 (observed 2026-08-28T04:10:29.121001+00:00)

## What it is
OpenChamber is an open-source agentic development environment providing a visual workspace (desktop app, web/PWA, and VS Code extension) for running, supervising, and reviewing work by the OpenCode AI coding agent. It adds session goals, multi-model runs, diff walkthroughs, app previews, and GitHub issue-to-PR workflows on top of the terminal-based agent.

## Use cases
- run and supervise AI coding agent sessions from a GUI instead of the terminal
- review and understand large AI-generated diffs with guided walkthroughs
- run the same task across multiple models and compare or fuse results
- manage AI agent work remotely from phone or browser
- start agent sessions from GitHub issues and open pull requests
- schedule recurring agent prompts on a cron schedule
- inspect a running web app and send element context to the agent

## When to choose
- you use OpenCode and want a visual control room for agent sessions
- you need to supervise long-running agent goals across devices
- you want to compare outputs from several models on one task
- you review AI-generated changes and want structured diff tours

## When to avoid
- you don't use OpenCode as your coding agent
- you prefer a purely terminal-based workflow
- you need an agent framework for building your own agents rather than driving OpenCode

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, chat-interface, developer-tools, gui, cli, editor
- domain: developer-tools, large-language-models, version-control
- platform: windows, browser, editor-plugin
- tags: opencode, agentic-coding, ai-coding-agent, pwa, vscode-extension, worktree-sessions, multi-model, remote-access, tunnel, github-integration, ai-agents, automation, macos, linux, web-server, desktop, mobile, nodejs, typescript

## Member repositories
- openchamber/openchamber (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:29.121001+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:22:37.891257+00:00, confidence not recorded.
  - readme: https://github.com/openchamber/openchamber (fetched 2026-08-28T04:10:29.121001+00:00, sha f4bb3cdab945)
  - homepage: https://openchamber.dev/ (fetched 2026-08-29T08:23:14.444304+00:00, sha 590f4df4e254)
  - site_page: https://docs.openchamber.dev/ (fetched 2026-08-29T08:23:14.453731+00:00, sha 822bf09faa22)
  - site_page: https://docs.openchamber.dev/install (fetched 2026-08-29T08:23:14.455466+00:00, sha 1e69d6e97b77)
  - site_page: https://openchamber.dev/changelog (fetched 2026-08-29T08:23:14.457119+00:00, sha d93ae7badd70)
- Data as of 2026-08-30T08:39:29.467469+00:00.