repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago
archit15singh/memori
Persistent memory for AI coding agents — SQLite + FTS5 + vector search in a single file
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 64%The biggest problem with AI memory isn't recall—it's stale facts [P] →
- PossiblePossibly related (embedding) · 57%We're building agents that can read millions of documents, but still forget a video they watched yesterday. →
- PossiblePossibly related (embedding) · 56%codebase-memory-mcp speeds AI coding agent queries - Let's Data Science →
- PossiblePossibly related (embedding) · 49%How to Optimize Vector Search When RAM Gets Too Expensive: On-Disk vs. In-Memory ANN Indexes - Towards Data Science →
- PossiblePossibly related (embedding) · 49%Show HN: Engrim – A universal, local-first SQLite memory engine for AI CLIs →
Covers
Covers (incoming)
Related across the graph
newsWe're building agents that can read millions of documents, but still forget a video they watched yesterday.newsHow to Optimize Vector Search When RAM Gets Too Expensive: On-Disk vs. In-Memory ANN Indexes - Towards Data Sciencenewscodebase-memory-mcp speeds AI coding agent queries - Let's Data SciencenewsThe biggest problem with AI memory isn't recall—it's stale facts [P]newsShow HN: Engrim – A universal, local-first SQLite memory engine for AI CLIs