Jev Users
← All projects

jevals

openlayer-ai/jevals MIT Python Eval & Align

rank#133
What it does

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.

Numbers
Stars
48
Forks
2
Open issues
0
Last push
today

Star history starts building from the first daily refresh.

agentsevalsguardrailsjevllmllm-evaluationragastypesafe

Open on GitHub → Homepage

More in Eval & Align