From GitHub
- GitHub stars
- 849
- Last code update
- 2026-08-07
AML-memory
A fixed evaluation harness and leaderboard for comparing LLM agent memory systems.
Why it made the shelf
It is an open-source evaluation harness and tool for testing and benchmarking LLM agent memory systems.
Seen on
- First seen
- 2 months ago
- Best score
- 1 points
Official signals
What the source shows.
Sourced facts from the places where this tool ships.
Public trail
Where it showed up
1 reference from 1 publisher.
- First trace
- Hacker News2 months ago
- 01Hacker NewsFirst trace
A fixed harness for comparing LLM agent memory systems