Your Agent Isn't Losing Memory. It's Rotting.

说明与用途

AI 代理因压缩、漂移和噪声而失去上下文。解决方案是使用语义索引、将决策存储在 Markdown 容器中、将知识转化为技能，并按半衰期分层内存。

问题

AI agents lose useful context over time, leading to incorrect decisions and degraded performance.

结果

Agents now run week‑long cycles with significantly less context decay, improving reliability without relying on larger prompt windows.

工作流

• Summarize interactions into executable facts with explicit schemas.
• Store lessons and decisions in a plain‑markdown vault and index with embeddings in SQLite.
• Convert lessons into triggered skills that load on demand.
• Layer memory by half‑life: instant preferences, entity facts, long‑lived conventions.
• Cap and prune the always‑on store on a schedule.
• Retrieve relevant slices on demand instead of carrying full context.
• Maintain a single source of truth for shared rules in the vault.
• Rebuild the index on a cron job to keep it up‑to‑date.

证据

Summarize to executable facts, not prose. Emit decisions and constraints as explicit, fixed‑schema entries the agent can act on.

来源

Move memory out of the session into a semantic index. Our biggest win. Keep lessons and decisions in a plain markdown vault, index with embeddings, and search returns meaning, not exact strings.

来源

Turn knowledge into skills, not notes. A lesson read once and never referenced is a lesson that rots. The durable form is a skill: a procedure loaded on demand behind a trigger, pulled into context exactly when it applies.

来源

Layer memory by half‑life. Instant preferences live in a compact always‑on store; entity facts in a structured store you can query; long‑lived conventions in a vault you load on purpose.

来源