# FailproofAI

## Docs

- [Architecture](https://docs.befailproof.ai/architecture.md): How the hook handler, config loading, and policy evaluation work internally
- [Built-in Policies](https://docs.befailproof.ai/built-in-policies.md): All 39 built-in policies that catch common agent failure modes
- [View sessions](https://docs.befailproof.ai/cli/dashboard.md): Launch the dashboard to browse agent sessions and manage policies
- [Environment variables](https://docs.befailproof.ai/cli/environment-variables.md): Configure failproofai behavior with environment variables
- [Hook handler (internal)](https://docs.befailproof.ai/cli/hook.md): The subprocess Claude Code calls on each tool event
- [Install policies](https://docs.befailproof.ai/cli/install-policies.md): Enable policies so they run on every agent tool call
- [List policies](https://docs.befailproof.ai/cli/list-policies.md): See which policies are enabled, their parameters, and custom policies
- [Uninstall policies](https://docs.befailproof.ai/cli/remove-policies.md): Remove hook entries from Claude Code's settings
- [Check version](https://docs.befailproof.ai/cli/version.md): Print the installed failproofai version
- [Configuration](https://docs.befailproof.ai/configuration.md): Config file format, three-scope system, and merge rules
- [Custom Policies](https://docs.befailproof.ai/custom-policies.md): Write your own policies in JavaScript - enforce conventions, prevent drift, detect failures, integrate with external systems
- [Dashboard](https://docs.befailproof.ai/dashboard.md): Monitor agent sessions, review tool calls, and manage policies
- [Examples](https://docs.befailproof.ai/examples.md): How to set up hooks for Claude Code and the Agents SDK
- [For agents](https://docs.befailproof.ai/for-agents.md): Add Failproof AI knowledge to your coding agent in one command. Works with Claude Code, Cursor, Windsurf, and more.
- [Getting started](https://docs.befailproof.ai/getting-started.md): Install failproofai, enable policies, and let your agents run reliably
- [Failproof AI](https://docs.befailproof.ai/introduction.md): FailproofAI gives AI agents 39 built-in failure policies that catch loops, secret leaks, destructive tool calls, and more in a single install.
- [Package Aliases](https://docs.befailproof.ai/package-aliases.md): Registered typosquat-prevention aliases and how they work
- [Testing](https://docs.befailproof.ai/testing.md): Unit tests, E2E tests, and test helpers

## OpenAPI Specs

- [openapi](https://docs.befailproof.ai/api-reference/openapi.json)

## Optional

- [GitHub](https://github.com/failproofai/failproofai)
- [npm](https://www.npmjs.com/package/failproofai)
- [Slack](https://join.slack.com/t/failproofai/shared_invite/zt-3v63b7k5e-O3NBHmj8X6n9gZSGDx6ggQ)