Re:Remembra – Open-source semantic memory for AI agents
by remembradev on Wednesday March 11, 2026 @09:13AM
(#47335139)
Great question on conflicts - this is something we spent a lot of time on.
Remembra uses temporal edges on the knowledge graph. When you store contradictory info ("user prefers Python" then later "user prefers Rust"), we don't just overwrite - we track both with timestamps and can:
1. Return the most recent by default
2. Surface contradictions explicitly when queried
3. Let you query point-in-time ("what did user prefer in January?")
For bad data, we have a few approaches:
- Confidence scoring on memories
- GDPR-compliant forget() to purge specific memories
- Audit logging so you can trace what was stored and when
You're right that memory quality is critical. Our benchmark focus (100% on LoCoMo) is specifically about retrieval accuracy - getting the right memory when you need it, not just any memory that keyword-matches.
Would love to hear how testing goes if you try it.
Remembra uses temporal edges on the knowledge graph. When you store contradictory info ("user prefers Python" then later "user prefers Rust"), we don't just overwrite - we track both with timestamps and can:
1. Return the most recent by default 2. Surface contradictions explicitly when queried 3. Let you query point-in-time ("what did user prefer in January?")
For bad data, we have a few approaches: - Confidence scoring on memories - GDPR-compliant forget() to purge specific memories - Audit logging so you can trace what was stored and when
You're right that memory quality is critical. Our benchmark focus (100% on LoCoMo) is specifically about retrieval accuracy - getting the right memory when you need it, not just any memory that keyword-matches.
Would love to hear how testing goes if you try it.