GitHub · Python
openlayer-ai/jevals
Agent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya.
- Stars
- 117
- Forks
- 13
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: agents, evals, guardrails, jev, llm, llm-evaluation, ragas, typesafe
Latest data point: Nov 21, 2026 · 117 stars · 13 forks