About CodeCord
An open-source platform for agentic coding automation — design, run, and monitor multi-step workflows powered by your choice of AI provider.
What is CodeCord?
CodeCord is a provider-agnostic agentic coding environment. Build reusable workflows from composable actions — code review, test generation, refactoring, PR automation, and more. Use GitHub Copilot, Anthropic Claude, or both.
Workflows are event-sourced and resumable — if a run is interrupted it picks up exactly where it left off. Every action is recorded as an immutable fact, giving you a full audit trail and the ability to replay or debug any execution.
The platform ships as a native Electron desktop app with direct filesystem access and deep OS integrations.
Composable workflows
Reusable actions, stages, and workflows that nest into development pipelines.
Local CI replacement
Run CI pipelines locally with AI agents — no remote runners needed.
Dev container support
Agents run in dev containers for isolated, reproducible environments.
Multi-provider AI
GitHub Copilot, Anthropic Claude, and more providers coming.
Open source
CodeCord is fully open source. The entire platform — desktop app, workflow engine, and all supporting packages — lives in a public monorepo on GitHub. Contributions, issues, and feedback are welcome.
codecord-dev/codecord
Main monorepo — desktop app, web app, workflow engine, and all packages.
codecord-dev organization
GitHub organization — all public repositories and project activity.
How to contribute
Fork & clone
Fork the repository on GitHub and clone it locally. The repo uses pnpm workspaces — run pnpm install from the root.
Pick an issue
Browse open issues on GitHub. Issues tagged "good first issue" are a great starting point for new contributors.
Open a PR
Make your changes, ensure tests pass with pnpm run test, and open a pull request with a clear description.
Author
More details coming soon.
Author details placeholder
This section will be filled in later.