Expired50% confidenceFactExact time
Claude-mem uses a vector database for hybrid search, combining semantic similarity and keyword matching retrieval strategies, with the entire memory injection process consuming only about 50 additional tokens of overhead.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Claude-mem: The Open-Source Memory System That Stops AI from Forgetting
bilibili锋芒AI6/4/2026
Related Claims
UnverifiedVector retrieval relies on vector databases for fuzzy matching and cannot precisely express structural relationships, whereas graph retrieval uses graph databases as the storage medium and is specifically optimized for multi-hop traversal queries.70% similarUnverifiedHybrid Search combines Dense Retrieval with sparse retrieval (BM25).64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/46866API
curl https://kongchang.com/api/v1/knowledge/claims/46866MCP
get_claim(id=46866)