Show HN: NexusMem – Local context memory engine for AI coding agents
NexusMem is a local‑first persistent memory engine designed for AI coding assistants. It records repository events, shell commands, documentation, and conversation transcripts in an on‑disk SQLite database and retrieves relevant context within a token budget. The system operates offline, combines BM25 keyword matching with vector search, and integrates with Model Context Protocol tools.
- ▪NexusMem stores data locally in a .nexusmem SQLite database using FTS5 and sqlite‑vec, eliminating cloud dependencies and telemetry.
- ▪It normalizes diverse sources such as git commits, shell history, markdown docs, and optional AI conversation logs into a unified MemoryNode schema for ranking.
- ▪Hybrid search fuses exact keyword matching (BM25) with semantic vector similarity via Reciprocal Rank Fusion, falling back to BM25 if the local Ollama model is unavailable.
- ▪Retrieval scores combine relevance, signal strength, and recency, and results are packed to respect a caller‑specified token budget.
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,230 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/yaminbakoh4-dot/NexusMem |
| Publication time | Mon, 10 Aug 2026 06:34:23 +0000 |
| Retrieval time | 2026-08-10T06:35:44.152Z |
| Last seen | 2026-08-10T06:35:44.152Z |
| 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 | 4gTSz2rRyilt · 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
NexusMem A local-first persistent memory engine for AI coding agents (Claude Code, Cursor, MCP-based agents). AI coding assistants forget context once a session ends, and re-uploading the entire repository as context on every request is slow and expensive. NexusMem records local machine events — git history, shell commands, docs, and conversation transcripts — into an on-disk SQLite database, returning only the relevant context slice within a strict token budget. All data remains local on your machine. No cloud dependencies, accounts, or telemetry. Design Principles 100% Local-First: SQLite database stored in .nexusmem/ inside your repository using sqlite-vec and FTS5. Works fully offline.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.