Claude Code plugin and CLI that check a coding agent's completion claims against its own transcript.
Check AI agent success claims against trace evidence instead of trusting the final message.
Distil an expensive LLM API call on a narrow task into a small local model served behind an OpenAI-compatible cascade.
Anthropic, PBC
Visionary sponsor
Bloomberg
Visionary sponsor
Hudson River Trading
Visionary sponsor
Meta
Visionary sponsor
NVIDIA
Visionary sponsor
Microsoft
Sustainability sponsor
Depot
Continuous Integration
AWS
Cloud computing and Security Sponsor
Datadog
Monitoring
Fastly
CDN
Google
Download Analytics
Sentry
Error logging
StatusPage
Status page