Introduction

Featherlane AI is an open-source runtime for defining, enforcing, and replaying trust policies across agents, services, and humans in the loop.

These docs are a work in progress. The site itself was just scaffolded — content migration is happening section by section.

Where to start

• Get started — install, run the demo, write your first policy.
• Concepts — architecture, policy model, agent profiles, plugin contract.
• Reference — CLI, HTTP API, Rust crates, TypeScript SDK, Python SDK.
• Guides — task-oriented walkthroughs.
• Project — roadmap, contributing, license.

For agents

This site is built to be readable by both humans and LLM agents. Agent-readable plain-text endpoints are available at:

• /llms.txt — curated index per the llms.txt convention
• /llms-full.txt — entire docs concatenated as plain markdown
• /docs/<path>.md — raw markdown source for any page