Why I Taught My AI Agent to Forget

说明与用途

构建了一个带忘记机制的本地技能记忆，用于存储程序知识，防止 AI 助手重复过去的错误，提高效率和准确性。

问题

The AI assistant kept re‑proposing outdated procedures, wasting time because it lacked procedural memory and could not filter relevant knowledge.

结果

Skillmem reduced redundant procedural suggestions, improved hit@5 to 0.871 and MRR to 0.622 on LongMemEval, and eliminated LLM calls during retrieval, making the system deterministic and fast.

工作流

• 1. Identify procedural knowledge gaps in agent behavior.
• 2. Build skillmem to store skills with trigger, steps, outcome, lessons.
• 3. Integrate skillmem into Claude Code via hooks and MCP tools.
• 4. Configure decay and lifecycle rules for skill strength.
• 5. Benchmark retrieval against LongMemEval to validate performance.
• 6. Monitor and adjust decay parameters and retrieval settings.

证据

skillmem stores exactly that shape. A skill looks like this: ...

来源

hit@5 0.871, MRR 0.622 on LongMemEval

来源

skillmem's write path is a SQLite INSERT plus Snowball stemming for the search index. No LLM in the loop.

来源