About this project

# Pi Agent Harness An AI agent toolkit providing unified LLM access, agent runtime infrastructure, and a coding agent CLI. ## Core Packages | Package | Description | |---------|-------------| | **@earendil-works/pi-ai** | Unified multi-provider LLM API supporting OpenAI, Anthropic, Google, and others | | **@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 | | **@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 | ## Key Features - **Unified LLM API**: Interact with multiple providers (OpenAI, Anthropic, Google, etc.) through a single interface - **Agent Runtime**: Full agent loop with tool calling capabilities and state management - **Coding Agent CLI**: Interactive command-line coding agent for development workflows - **Containerization Support**: Multiple sandboxing patterns including Gondolin micro-VM, Docker, and OpenShell for isolated execution ## Security & Supply Chain Pi enforces strict dependency management: - Direct external dependencies are pinned to exact versions - Lockfile changes are blocked by default without explicit approval - npm audit runs regularly in CI, including signature verification - Shrinkwrap generation validates dependency lifecycle scripts against an allowlist ## Development Built with Node.js and TypeScript using a monorepo structure. Key commands include `npm install --ignore-scripts`, `npm run build`, and `./test.sh`. ## License MIT