AML-memory/agent-memory-leaderboard
A public evaluation platform and leaderboard for long-term agent memory systems.
Collecting fresh signals — velocity needs a few days of history.
collecting data…
star history
Agent Memory Leaderboard (AML) provides a standardized evaluation protocol and public leaderboards for long-term memory systems used by agents, with Textual, Coding, and Multimodal Memory tracks. Participating systems expose Add and Search interfaces, while the platform handles answer generation or agent execution, scoring, result review, and leaderboard publication. It also organizes an Agent Memory Challenge with submission and evaluation cycles.
Frequently asked
- What is AML-memory/agent-memory-leaderboard?
- A public evaluation platform and leaderboard for long-term agent memory systems.
- Is agent-memory-leaderboard open source?
- Yes — AML-memory/agent-memory-leaderboard is an open-source project tracked on heatdrop.
- What language is agent-memory-leaderboard written in?
- AML-memory/agent-memory-leaderboard is primarily written in Python.
- How popular is agent-memory-leaderboard?
- AML-memory/agent-memory-leaderboard has 1.1k stars on GitHub.
- Where can I find agent-memory-leaderboard?
- AML-memory/agent-memory-leaderboard is on GitHub at https://github.com/AML-memory/agent-memory-leaderboard.