If you’re planning to find an open-source Agent Harness for secondary development to build your own AI-native product, Pi Durable, released alongside Pi 1.0, is a highly worthwhile foundational choice to consider.

For teams doing product-level development, many open-source frameworks are either too tightly bound to terminal CLIs or overly massive and bloated, making it extremely laborious to transform them into backend services. Pi Durable precisely addresses this pain point.

Using it as the core foundation, it can help you achieve several extremely critical effects:

First, automatic resumption of crashed long tasks. Each step of Agent execution is abstracted as an independent task with checkpoints. Whether it’s a backend container restart, server maintenance, or process abnormal exit, the new process can precisely locate the breakpoint and continue running once connected to storage—no need to re-consume tokens and retraverse the long context from scratch.

Second, cross-environment and edge deployment. The framework core is entirely written in TypeScript, with built-in SQLite and JSONL storage free of any Node native API bindings. It can run not only locally and on servers but also deploy directly to lightweight edge environments like Bun or Cloudflare Durable Objects.

Third, multi-end collaboration and concurrent branching. A single instance supports running multiple parallel session branches simultaneously, such as a main task spawning multiple sub-threads. Application state is stored externally in document form, allowing multiple frontend interfaces or collaborators to mount simultaneously, observe the execution process in real time, or even intervene midway.

Why choose it for secondary development? The core benefits lie in its restraint and decoupling:

The entire core codebase is only about 15,000 lines, with no superfluous historical baggage—the code volume can even fit directly into a large model’s context, letting AI assist you in hacking it around.

More importantly, it separates the control plane and execution plane very cleanly: scheduling and storage only handle task flow, while specific file reads/writes and terminal executions are delegated to pluggable independent environments. You can place the “brain” in cloud-edge setups and the “hands and feet” on users’ local machines or remote isolated sandboxes.

Plus, with backend automations for long-context compression, hot-swappable tools, and other engineering details, if you want to quickly build a highly reliable Agent system on an ultra-minimal base, this foundation will save a ton of time reinventing the wheel.

Official project address:

earendil-works/pi

Source: https://github.com/earendil-works/pi

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

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:

curl -fsSL https://pi.dev/install.sh | sh

On Windows:

powershell -c "irm https://pi.dev/install.ps1 | iex"

The installer pins all dependencies and updates Pi with pi update. Alternatively, install directly with npm, which does not pin transitive dependencies:

npm install -g --ignore-scripts @earendil-works/pi-coding-agent

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.

See the documentation for full setup and usage instructions, or visit pi.dev for demos.

Run with Nix

nix run github:earendil-works/pi/stable

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.

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 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.
• 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.
• 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.

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