Open source freemium
In these stacks
LicenseMIT
PriceFree tier
UsageNo model cost
Model supportmulti
Languagespython, typescript
GitHub stars5.7k
Last activity2026-06-25
VerifiedThu Jun 25 2026 00:00:00 GMT+0000 (Coordinated Universal Time)
Verified byseed
A tool focused on tracing and evaluating agent runs, sessions, and tool calls rather than generic LLM calls.
Strengths
- Agent-session mental model fits agentic apps
- Easy SDK integration
Tradeoffs
- Cloud-only currently
- Newer and less mature than incumbents