Evals as code for LLM apps and agents. Write tasks and graders in YAML, run them in CI, fail the build on regressions.
Self-hostable disposable sandboxes for AI agents, with snapshot, rollback, and fork.
Open-source daily voice check-in agent for older adults living alone, with caregiver alerts.
Benchmark harness for real-time voice agents: latency, barge-in, and turn-taking measured from the audio.
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