Show HN

Agent Memory Leaderboard

by @IreneAI

Agent Memory Leaderboard – first public results for AI memory systems We just released the first public results from the Agent Memory Leaderboard (AML). The first evaluation focuses on Text Memory across two tracks: - Open-source Methods - Commercial Products 136 teams registered, and 69 representative memory frameworks completed the first evaluation. Commercial Products — Text Memory: 1. MemoraX — 58.02 2. MemOS — 45.89 3. NTES-MEMORY-SMART — 44.21 The benchmark uses a common evaluation framework and a clearer system boundary: Memory system: Add → Search Benchmark: Answer → Eval The goal is to make memory-system results more comparable and reproducible.

Discover more builders

Builderlust is an endless, joyful scroll of real projects people are shipping right now. Get the app to keep finding your next spark of inspiration.

📱 Coming soon to iOS & AndroidOpen in the app