Note

Personal fork: This is Hypnotox's personal fork of earendil-works/pi. It tracks upstream while carrying changes that are not part of the official project, including:

• ExtensionAPI.queueCommand() queues a registered extension command for FIFO execution after the active agent fully settles, using a fresh command context and no model-visible user message.

Builds are published as versioned, checksummed GitHub Release assets, not as official @earendil-works npm releases. Tags use fork-v<upstream-version>.<fork-revision>, for example fork-v0.84.1.2. The documentation below otherwise describes the upstream project unless stated differently.

Install this fork

Choose a release tag and install its tarball directly with npm:

TAG=fork-v0.84.1.2
npm install -g "https://github.com/hypnotox/pi/releases/download/${TAG}/pi-coding-agent-${TAG}.tgz"

Pin the tag in installation scripts and lockfiles. This package keeps the official @earendil-works/pi-coding-agent package identity but is built from this fork.

Syncing upstream and publishing a fork build

Fork releases synchronize the fork with upstream/main; they do not use the upstream project's changelog audit or release scripts.

1. Start from a clean main that matches origin/main, then fetch upstream branches and tags.
2. Merge the full upstream/main tip with a merge commit. Resolve conflicts by retaining both upstream changes and intentional fork patches, including the personal-fork workflow and the removal of upstream-only workflows.
3. Verify the current upstream release tag is an ancestor of the merge, packages/coding-agent/package.json has that upstream version, and the fork-only patches and regression tests remain present.
4. Run npm run check and the relevant fork regression tests. The tag workflow runs the full build and non-e2e test suite again.
5. Create an annotated tag named fork-v<upstream-version>.<fork-revision>. Start at revision 1 for a new upstream version; increment it for later fork builds of the same version.
6. Push main, then push the tag:

git push origin main
git tag -a fork-v0.84.3.1 -m "Fork build 0.84.3.1"
git push origin fork-v0.84.3.1

The tag triggers the personal-fork workflow, which validates the tag and upstream ancestry, builds, checks, tests, verifies the packed CLI, and publishes a checksummed GitHub Release.

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

Package	Description
@earendil-works/pi-telemetry	Vendor-neutral telemetry contracts, reference adapter, conformance tests, and typed schemas
@earendil-works/pi-ai	Unified multi-provider LLM API (OpenAI, Anthropic, Google, etc.)
@earendil-works/pi-agent-core	Agent runtime with tool calling and state management
@earendil-works/pi-coding-agent	Interactive coding agent CLI
@earendil-works/pi-tui	Terminal UI library with differential rendering

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

Permissions & Containerization

Pi does not include a built-in permission system for restricting filesystem, process, network, or credential access. By default, it runs with the permissions of the user and process that launched it.

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         # Refresh model data, then build all packages
npm run build:offline # Rebuild using existing model data without network access
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)

Building standalone binaries from release source

GitHub releases include a versioned source archive covered by the release's SHA256SUMS file. Extract it and run the same build script used for the official standalone binaries:

VERSION="<release-version>"
tar -xzf "pi-${VERSION}-source.tar.gz"
cd "pi-${VERSION}"
./scripts/build-binaries.sh --offline-model-data --platform linux-x64 --out "$PWD/out"

The source archive includes the generated provider model data used for the release. --offline-model-data builds with that snapshot instead of refreshing it from live provider catalogs. The script still installs dependencies, builds the monorepo, compiles the Bun executable, and stages its runtime assets. Package maintainers who provide dependencies separately can pass --skip-install --skip-deps.

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

pi.dev domain graciously donated by


exe.dev