Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. 40 built-in policies, a local dashboard, no account required with a generous free cloud plan

The AI toolkit for building reliable browser automations

File-backed workflow harness for reliable Claude Code and Codex sessions.

The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.

Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discovery defines what to build, Delivery executes autonomously until criteria pass. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and more. No SDK. No package. Markdown + YAML + bash.

Lint rules for your AI agent's discipline, not its code