[opensourcedex]

pi is a free, open source ai assisted coding project written in TypeScript and released under MIT. It has 106,586 GitHub stars, 13,437 forks and 202 open issues, and was last pushed 5 hours ago. On this registry it ranks #2 of 24 tracked projects in AI Assisted Coding, with 5 head-to-head comparisons available. It gained 2,202 stars over the last 6 tracked days.

What is pi?

What it is

Pi is a modular agent toolkit written in TypeScript for building and running terminal-based AI coding agents. It lives in the developer tooling ecosystem and provides composable packages for LLM integration, agent orchestration, and terminal UI rendering. The project centers on @earendil-works/pi-coding-agent, an interactive CLI agent, supported by core runtime, AI abstraction, and TUI libraries.

It solves the problem of fragmented agent development by unifying multi-provider LLM access, tool calling, state persistence, and terminal interaction into a single extensible framework. Developers can compose custom agents with built-in tools (e.g., file editing, shell execution) and extend behavior via plugins or external services, avoiding vendor lock-in or monolithic agent implementations.

Key capabilities

  • Unified multi-provider LLM API supporting OpenAI, Anthropic, Google, and others via @earendil-works/pi-ai
  • Agent runtime with tool calling, state management, and extensible tool registries in @earendil-works/pi-agent-core
  • Interactive coding agent CLI with file editing, shell command execution, and plan-execution loops
  • Terminal UI library with differential rendering for responsive, incremental output updates
  • Standalone application-composition runtime (@earendil-works/chord) for services, RPC, and plugins
  • Vendor-neutral telemetry contracts and conformance tests in @earendil-works/pi-telemetry
  • Containerization patterns (Docker, micro-VM, OpenShell) for sandboxing agent actions

Who uses it and how

  • Developers embed the coding agent CLI as a customizable pair programmer in local terminals
  • Teams build internal agent workflows by composing pi-agent-core with custom tools and policies
  • Security-conscious users deploy Pi inside Docker containers or Linux micro-VMs to restrict filesystem and network access
  • Plugin authors use chord to build and hot-reload service extensions without restarting the agent

Getting started

Install globally via npm install -g @earendil-works/pi-coding-agent or run from source using ./pi-test.sh. A Docker image is available at ghcr.io/earendil-works/pi. Official binaries are built from release source archives using ./scripts/build-binaries.sh.

When to use it — and when not to

Use Pi when you need a self-hosted, fully customizable coding agent with fine-grained control over tooling, LLM providers, and execution boundaries. Avoid it if you require out-of-the-box enterprise permissions, audit logging, or managed infrastructure—Pi offers no built-in RBAC or telemetry backend. Self-hoster must manage LLM API keys, storage for agent state, and optionally SMTP for notifications. Its lack of native sandboxing means users must enforce isolation via containerization.

project readme (upstream, from github) — read inline

pi logo

Discord npm

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.

To learn more about Pi:

All Packages

Package Description
@earendil-works/chord Standalone application-composition runtime for services, replicated state, RPC, and plugins
@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 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 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:

License

MIT

pi.dev domain graciously donated by


exe.dev

Frequently asked questions

Is pi free to use?

pi is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does pi do?

Minimal terminal coding agent you can fully customize

What is pi written in?

pi is primarily written in TypeScript. Its source is publicly available at https://github.com/earendil-works/pi, and it has 106,586 GitHub stars.