The Eval Index / Observability / #28

future-agi/future-agi

by future-agi · Observability · updated today

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

77
momentum
1,142
stars
249
forks
#28
rank
aiai-gatewayevalsllmobservabilitysimulation
View on GitHub →