Pi ships with powerful defaults but skips features like sub-agents and plan mode. Ask Pi to build what you want, or install a package that does it your way.
The installer pins all dependencies and updates Pi with pi update. Alternatively, install directly with npm, which does not pin transitive dependencies:
Pi requires Node.js 22.19 or newer. The macOS, Linux, and Windows installers can install it if needed. Pi does not require dependency lifecycle scripts for a normal npm installation.
Start Pi in the directory where you want it to work:
cd /path/to/project
pi
For a built-in AI provider, run /login inside Pi to connect a subscription or API key. Then give Pi a task.
stable points at the latest release. Install it with nix profile add github:earendil-works/pi/stable and update with nix profile upgrade pi. Use a release tag such as github:earendil-works/pi/v1.0.0 to pin a version, or github:earendil-works/pi for unreleased changes on main. Nix builds Pi from source.
Supports ARM64 and x86-64 on Linux and macOS. Use nix build . or nix run . to build or run your checkout.
Nix builds are offline, so the bundled model data comes from a pi.dev model catalog revision pinned in nix/model-catalog.json. At runtime, Pi still overlays newer catalog data from pi.dev as usual. The Nix workflow replaces the pin on main when it no longer matches the checkout, for example after a provider is added or gains a new model type. To refresh it by hand:
npm run update:model-catalog-pin
Packages
This monorepo contains the Pi CLI and its supporting libraries.
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.
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)
Using local packages outside the monorepo
Build every public package into one coherent local artifact set:
npm run pack:packages -- --out .artifacts/pi-packages
This refreshes model data before building pi-ai. To avoid network access when
model data is already hydrated, pass --offline-model-data.
Then configure an external project to consume one package and resolve all of
its Pi dependencies from the same artifact set. npm is the default:
Repeat --package for each direct dependency. The command updates the
consumer’s package.json with content-addressed local file: references. It
writes transitive overrides to package.json for npm or pnpm-workspace.yaml
for pnpm. Keep the artifact directory available while installing or updating
the consumer. Re-run both commands after changing Pi source.
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 archive includes release model data and native prebuilds. --offline-model-data uses that model data without refreshing provider catalogs. The script installs dependencies and builds the executable with its runtime assets; pass --skip-install if dependencies are already provided.
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 install lock.
The pi.dev installer installs from packages/coding-agent/install-lock/, generated from the root lockfile, to pin transitive deps. The npm package does not pin transitive deps.
Local release smoke tests and npm publication use the same tarball packer; npm publishes the validated tarballs rather than repacking workspace directories.
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.
Install lock 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.
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:
Pi
Pi is a minimal, extensible agent harness that you can make your own.
Adapt Pi to your workflows, not the other way around. Customize Pi with extensions, skills, prompt templates, and themes. Bundle them as Pi packages and share via npm or git.
Pi ships with powerful defaults but skips features like sub-agents and plan mode. Ask Pi to build what you want, or install a package that does it your way.
Use Pi interactively, automate it in print or JSON mode, control it over RPC, or build apps with the Pi TypeScript SDK. See OpenClaw for a real-world integration.
Getting started
Install the command-line interface:
On Windows:
The installer pins all dependencies and updates Pi with
pi update. Alternatively, install directly with npm, which does not pin transitive dependencies:Pi requires Node.js 22.19 or newer. The macOS, Linux, and Windows installers can install it if needed. Pi does not require dependency lifecycle scripts for a normal npm installation.
Start Pi in the directory where you want it to work:
For a built-in AI provider, run
/logininside Pi to connect a subscription or API key. Then give Pi a task.See the documentation for full setup and usage instructions, or visit pi.dev for demos.
Run with Nix
stablepoints at the latest release. Install it withnix profile add github:earendil-works/pi/stableand update withnix profile upgrade pi. Use a release tag such asgithub:earendil-works/pi/v1.0.0to pin a version, orgithub:earendil-works/pifor unreleased changes onmain. Nix builds Pi from source.Supports ARM64 and x86-64 on Linux and macOS. Use
nix build .ornix run .to build or run your checkout.Nix builds are offline, so the bundled model data comes from a pi.dev model catalog revision pinned in
nix/model-catalog.json. At runtime, Pi still overlays newer catalog data from pi.dev as usual. The Nix workflow replaces the pin onmainwhen it no longer matches the checkout, for example after a provider is added or gains a new model type. To refresh it by hand:Packages
This monorepo contains the Pi CLI and its supporting libraries.
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:
piand provider auth on the host while routing built-in tools and!commands into a local Linux micro-VM.piprocess in a local container for simple isolation.piprocess 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
Using local packages outside the monorepo
Build every public package into one coherent local artifact set:
This refreshes model data before building
pi-ai. To avoid network access when model data is already hydrated, pass--offline-model-data.Then configure an external project to consume one package and resolve all of its Pi dependencies from the same artifact set. npm is the default:
For a pnpm project, point
--consumerat the workspace root:Repeat
--packagefor each direct dependency. The command updates the consumer’spackage.jsonwith content-addressed localfile:references. It writes transitive overrides topackage.jsonfor npm orpnpm-workspace.yamlfor pnpm. Keep the artifact directory available while installing or updating the consumer. Re-run both commands after changing Pi source.Building standalone binaries from release source
GitHub releases include a versioned source archive covered by the release’s
SHA256SUMSfile. Extract it and run the same build script used for the official standalone binaries:The archive includes release model data and native prebuilds.
--offline-model-datauses that model data without refreshing provider catalogs. The script installs dependencies and builds the executable with its runtime assets; pass--skip-installif dependencies are already provided.Supply-chain hardening
We treat npm dependency changes as reviewed code changes.
.npmrcsetssave-exact=trueandmin-release-age=2to avoid same-day dependency releases during npm resolution.package-lock.jsonis the dependency ground truth. Pre-commit blocks accidental lockfile commits unlessPI_ALLOW_LOCKFILE_CHANGE=1is set.npm run checkverifies pinned direct deps, native TypeScript import compatibility, and the generated coding-agent install lock.packages/coding-agent/install-lock/, generated from the root lockfile, to pin transitive deps. The npm package does not pin transitive deps.pi update --selfuse--ignore-scriptswhere supported.npm ci --ignore-scripts, and a scheduled GitHub workflow runsnpm audit --omit=devplusnpm audit signatures --omit=dev.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, andpi-share-hf.You can also watch this video, where I show how I publish my
pi-monosessions.I regularly publish my own
pi-monowork sessions here:License
MIT
pi.dev domain graciously donated by

exe.dev