Show HN: Llmem – Local persistent memory for AI coding, no embeddings
llmem Local-first persistent memory for AI coding agents. Give Claude Code, Cursor, and other MCP clients a memory that survives across sessions — stored in a single SQLite file, retrieved with BM25, with no embeddings, no vector database, and no external API calls. Built for Claude Code, Cursor and other local agents via MCP (Model Context Protocol).
- ▪llmem Local-first persistent memory for AI coding agents.
- ▪Give Claude Code, Cursor, and other MCP clients a memory that survives across sessions — stored in a single SQLite file, retrieved with BM25, with no embeddings, no vector database, and no external API calls.
- ▪Built for Claude Code, Cursor and other local agents via MCP (Model Context Protocol).
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,940 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/netrixone/llmem |
| Publication time | Fri, 07 Aug 2026 08:40:08 +0000 |
| Retrieval time | 2026-08-07T08:50:41.544Z |
| Last seen | 2026-08-07T08:50:41.544Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | HxipwB3Tmrwz · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
llmem Local-first persistent memory for AI coding agents. Give Claude Code, Cursor, and other MCP clients a memory that survives across sessions — stored in a single SQLite file, retrieved with BM25, with no embeddings, no vector database, and no external API calls. Built for Claude Code, Cursor and other local agents via MCP (Model Context Protocol). Why llmem Local-first — Everything runs on your machine: one SQLite file (~/.llmem/data.db), no network dependencies, no per-query cost. No embeddings, no vector DB — Retrieval is BM25 lexical search with optional WordNet synonym expansion. The tradeoff is deliberate: weaker on heavy paraphrase than an embedding model, but zero external services to run and zero cost per query.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.