Tier 3 · Agent memory Agent memory · fetched 2026-07-02
openclaw-self-memory
Long-term memory for agents with hybrid search, reranking, and explicit 'compaction protection': preserving what matters when the context window fills and compaction wipes raw conversation detail.
View source on GitHubKey takeaways
- 01
Compaction is the moment memories are lost - protect against it explicitly
- 02
Hybrid search + reranking for recall quality
- 03
Write session-survival summaries before compaction hits
Flows built on this research
Memory & Context
Session Summaries That Survive Compaction
Write durable session summaries at the right moments so knowledge outlives compaction and process restarts.
4 steps · 60-90 minutes
Memory & Context
Implement Context Compaction
Keep long agent sessions alive by compacting old conversation into structured summaries before the context window fills.
4 steps · 90-120 minutes