Memorybench
Benchmarks a custom memory implementation in a project against Supermemory, Mem0, Zep, and baseline
by supermemoryai
The skill
Benchmarks a custom memory implementation in a project against Supermemory, Mem0, Zep, and baseline systems using the MemoryBench framework, generating a TypeScript provider adapter, registering it, and running LoCoMo, LongMemEval, or ConvoMem datasets with bun. Use when you have built a custom memory, context, or RAG system and need accuracy and latency comparisons against other memory providers.
This skill's licence does not allow redistribution, so the store does not show its text. Read it at the source.
Use this skill
Connect your agent to the Skill Store MCP server and ask for it by ref: supermemoryai/memorybench-21093557894.
Details
- Publisher
- supermemoryai
- Category
- AI & Agents › Agent evaluation
- Updated
- 2026-10-14
References
More from supermemoryai
- Supermemory Cli Use the Supermemory CLI (`supermemory` 5.x on npm) from the terminal or from scripts and agents.
- Supermemory Build with the Supermemory v5 API and SDKs (TypeScript `supermemory` 5.x, Python `supermemory` 5.…
- Svg Animations Create beautiful, performant SVG animations and illustrations.
- Supermemory Supermemory is a state-of-the-art memory and context infrastructure for AI agents.