letta-evals

Eval harness for stateful Letta agents; configurable suites and grading (LLM or rule-based) so you can measure what you ship.

memorypython

Stars: 83
Adoption surface: mostly simple
Autonomy: headless
Recovery: none
License: ✅ open-source
Category: Evaluation and benchmarking harnesses

Repository ↗ Example: LoCoMo memory benchmark ↗

Related in Evaluation and benchmarking harnesses

Agent Lightning
SWE-bench
AgentBench
inspect_ai
WebArena
ClawBench

Maintain letta-evals? Add the badge

Paste this into your README so readers can find the list and see how letta-evals compares:

[![Best of Agent Harnesses](https://img.shields.io/badge/%F0%9F%8F%86_Best_of-Agent_Harnesses-5ac4bf)](https://github.com/RyanAlberts/best-of-Agent-Harnesses)