Memory for agents
A local-first memory system for AI agents. Store text memories and whole codebases, retrieve them with hybrid semantic + lexical search, and let a self-organizing topic tree + artifact graph + concepts keep everything structured as it grows.
Latest releases
Section titled “Latest releases”The versions below are fetched from the npm registry at build time — this site rebuilds automatically after every publish.
| Package | Version | Published |
|---|---|---|
@ponraaj/dimple-sdk |
v0.0.0-alpha.6 | 2026-08-07 |
@ponraaj/dimple (CLI) |
v0.0.0-alpha.6 | 2026-08-07 |
What is Dimple?
Section titled “What is Dimple?”Problem: naive memory stores scan every vector per query (cost grows with memory count), return flat results with no structure, and give the agent no notion of why a memory is relevant, what supersedes it, or what contradicts it.
Approach — three structures maintained automatically by a durable background worker:
- Topic tree — memories are routed by embedding similarity into tree leaves. Queries descend the tree (beam search on centroids) and only score the reached leaves: search cost grows with depth, not with memory count. A durable worker splits overflowing leaves and merges underflowing ones with deterministic algorithms — same embeddings ⇒ same tree, anywhere.
- Hybrid retrieval — vector (cosine) + FTS5 lexical legs fused with Reciprocal Rank Fusion, optional recency boost, and per-result graph context.
- Artifact graph + concepts — directed
memory_supports/memory_supersedes/memory_contradicts/code_callsedges written by structural rules, code indexing, the agent, and the optional dream job (LLM classification of candidates + deterministic concept clustering). Retrieval consumes the graph: superseded memories demote, conflicts surface, supports ride along as provenance.
All structural decisions are deterministic; everything is durable (two SQLite files — or a Turso remote database — and resume-safe jobs).