New issues and PRs from new contributors are auto-closed by default. Maintainers review auto-closed issues daily. See CONTRIBUTING.md.

Pi Agent Harness

This is the home of the Pi agent harness project including our self extensible coding agent.

• @earendil-works/pi-coding-agent: Interactive coding agent CLI
• @earendil-works/pi-agent-core: Agent runtime with tool calling and state management
• @earendil-works/pi-ai: Unified multi-provider LLM API (OpenAI, Anthropic, Google, …)

To learn more about Pi:

• Visit pi.dev, the project website with demos
• Read the documentation, but you can also ask the agent to explain itself

All Packages

For Slack/chat automation and workflows see earendil-works/pi-chat.

Permissions & Containerization

Pi runs with the permissions of the user and process that launched it. The built-in permission system can ask, allow, or deny tool calls before they run, but it is not a sandbox and does not restrict the host process, installed extensions, package installs, or child processes after they are started.

By default, Pi uses the full-access permission preset, so ordinary tool calls do not prompt. Choose a stricter preset with permissionPreset in settings or --permission-preset on the CLI:

• full-access: allow all permission checks
• workspace: allow workspace read, search, edit, and shell tools; ask for external-directory access
• read-only: allow read/search/list tools; ask before edits, shell commands, and external-directory access
• ask: restore prompt-on-unknown behavior

Explicit permission rules in settings and --permission CLI rules override the selected preset.

If you need stronger boundaries, containerize or sandbox Pi. See packages/coding-agent/docs/containerization.md for three patterns:

• Gondolin extension: keep pi and provider auth on the host while routing built-in tools and ! commands into a local Linux micro-VM.
• Plain Docker: run the whole pi process in a local container for simple isolation.
• OpenShell: run the whole pi process in a policy-controlled sandbox.

Contributing

See CONTRIBUTING.md for contribution guidelines and AGENTS.md for project-specific rules (for both humans and agents). Longer term plans for Pi can also be found in RFCs.

Development

npm install --ignore-scripts  # Install all dependencies without running lifecycle scripts
npm run build        # Build all packages
npm run check        # Lint, format, and type check
./test.sh            # Run tests (skips LLM-dependent tests without API keys)
./pi-test.sh         # Run pi from sources (can be run from any directory)

Supply-chain hardening

We treat npm dependency changes as reviewed code changes.

• Direct external dependencies are pinned to exact versions. Internal workspace packages remain version-ranged.
• .npmrc sets save-exact=true and min-release-age=2 to avoid same-day dependency releases during npm resolution.
• package-lock.json is the dependency ground truth. Pre-commit blocks accidental lockfile commits unless PI_ALLOW_LOCKFILE_CHANGE=1 is set.
• npm run check verifies pinned direct deps, native TypeScript import compatibility, and the generated coding-agent shrinkwrap.
• The published CLI package includes packages/coding-agent/npm-shrinkwrap.json, generated from the root lockfile, to pin transitive deps for npm users.
• Release smoke tests use npm run release:local to build, pack, and create isolated npm and Bun installs outside the repo before tagging a release.
• Local release installs, documented npm installs, and pi update --self use --ignore-scripts where supported.
• CI installs with npm ci --ignore-scripts, and a scheduled GitHub workflow runs npm audit --omit=dev plus npm audit signatures --omit=dev.
• Shrinkwrap generation has an explicit allowlist for dependency lifecycle scripts; new lifecycle-script deps fail checks until reviewed.

Share your OSS coding agent sessions

If you use Pi or other coding agents for open source work, please share your sessions.

Public OSS session data helps improve coding agents with real-world tasks, tool use, failures, and fixes instead of toy benchmarks.

For the full explanation, see this post on X.

To publish sessions, use badlogic/pi-share-hf. Read its README.md for setup instructions. All you need is a Hugging Face account, the Hugging Face CLI, and pi-share-hf.

You can also watch this video, where I show how I publish my pi-mono sessions.

I regularly publish my own pi-mono work sessions here:

• badlogicgames/pi-mono on Hugging Face

License

MIT