Pinned Loading

1. Gloss Gloss Public

   A local-first, privacy-preserving alternative to Google NotebookLM — Tauri 2, React 19, Rust, Ollama

   Rust 43

2. turbo-quant turbo-quant Public

   Rust implementation of TurboQuant, PolarQuant, and QJL — zero-overhead vector quantization for semantic search and KV cache compression (ICLR 2026)

   Rust 26 7

3. proveKV proveKV Public

   Two-tier, receipted, content-addressed KV-cache pool. fib_k4_n32 cold tier + turbo_8bit hot tier. 18-20% lossless dPPL on real 1.7B LLM. Successor to kv-lossless-11x (archived).

   Rust 4

4. semantic-memory-mcp semantic-memory-mcp Public

   MCP server wrapping semantic-memory — local-first knowledge management with evidence-scored retrieval, contradiction detection, and adaptive routing

   Rust 3 1

5. semantic-memory semantic-memory Public

   Hybrid semantic search library for Rust, SQLite + FTS5 + HNSW, built for AI agent memory systems

   Rust 2

6. agent-memory-kits agent-memory-kits Public

   Persistent local-first semantic memory for any agent: (Hermes, claude code, codex, etc..) : plugin (auto-recall hooks + MCP server) plus a language-agnostic codebase ingester.

   Python