Mnemos
Local vector memory for Claude Desktop with 3D conversation visualization
The Panel's Take
Claude Desktop has no memory across sessions. You close the window and it forgets everything. Mnemos is an open-source MCP server that fixes this by watching your conversation files in real-time, indexing them with local ONNX embeddings (MiniLM-L6-v2), and enabling hybrid semantic + keyword search — all without a single byte leaving your machine. The v1.1 release adds a genuinely striking feature: a 3D semantic visualization that maps your conversations into a clustered constellation using UMAP dimensionality reduction and Three.js. You can scrub through a chronological timeline and watch the knowledge graph build in real time. It is, frankly, prettier than it needs to be. Built on .NET 9, SQLite FTS5, and React/Vite, Mnemos is one of the more technically ambitious "Claude memory" projects to appear on HN this week. The offline-first, MIT-licensed approach puts it in a different league from cloud-synced alternatives.
Share this verdict
Mnemos verdict: SHIP 🚀 3 ships · 1 skip from the expert panel Full review: shiporskip.io/tool/mnemos-claude-desktop-local-memory-vector-semantic-3d-mcp-2026
Weekly AI Tool Verdicts
Get the next verdict in your inbox
7 critics review a new AI tool every day. Weekly digest — free.
Compare Mnemos with Others
Embed this verdict
Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.
<a href="https://shiporskip.io/api/badge-click/mnemos-claude-desktop-local-memory-vector-semantic-3d-mcp-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/mnemos-claude-desktop-local-memory-vector-semantic-3d-mcp-2026" alt="Mnemos Ship verdict on ShipOrSkip" width="360" height="90" /></a>[](https://shiporskip.io/api/badge-click/mnemos-claude-desktop-local-memory-vector-semantic-3d-mcp-2026)<iframe src="https://shiporskip.io/embed/mnemos-claude-desktop-local-memory-vector-semantic-3d-mcp-2026" title="Mnemos ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>The reviews
“This solves a real, painful problem with zero cloud dependency. The hybrid FTS5 + vector search is the right architecture — you get speed and semantic richness without compromising privacy. The .NET 9 stack is slightly niche but the setup looks smooth.”
“It is a one-person Show HN project posted literally today with 2 GitHub stars. The 3D visualization is cool but has nothing to do with actually improving recall quality. Also: how often do you actually need to search old Claude conversations vs. just starting fresh?”
“Local-first AI memory is the correct long-term architecture. Every AI system we rely on should have this kind of persistent, private, searchable context layer. Mnemos is a prototype of what OS-level AI memory will eventually look like, and seeing it built today matters.”
“The 3D constellation visualization genuinely excites me — there is art in watching your conversation history render as a navigable space. For writers and researchers who use Claude heavily, the ability to rediscover old threads through semantic search could unlock something meaningful.”