🧠 Local-first knowledge system for LLM agents — sqlite-vec + ONNX embeddings, no cloud/Docker/PyTorch dependency
-
Updated
May 24, 2026 - Python
🧠 Local-first knowledge system for LLM agents — sqlite-vec + ONNX embeddings, no cloud/Docker/PyTorch dependency
Robot Memory - Persistent memory system for AI robots. MCP Server + hybrid search + spatial retrieval.
The memory substrate for AI agents and developer tools. Git-versioned, file-native, MCP-first.
Find relevant information in your documents using natural language queries - no more keyword matching or manual browsing through hundreds of files. Built for speed and efficiency, this lightweight system searches through 500+ documents in under 300ms while using only 100MB of memory.
Personal Telegram knowledge base — forward anything, search via DM. Hybrid SQLite + FTS5 + vector + voice, MCP server for Claude.
SeekLink — hybrid semantic search for markdown vaults. Four-channel RRF fusion, MLX reranker, native CJK support. Fully local.
Persistent memory MCP for AI agents — SQLite, knowledge graph, 12 tools with ToolAnnotations
Persistent memory for Claude Code — invisible self-annotating metadata, semantic search, cross-project retrieval
Git-native, semantically-searchable memory storage for Claude Code. Captures decisions, learnings, and context as git notes with vector search.
Local Codex CLI prompt refinery: ingest JSON/JSONL histories, dedupe, embed (OpenAI), cluster (sqlite-vec), synthesize atomic/workflow prompts via Responses API (Structured Outputs). FTS5+vector search; Streamlit UI; Typer CLI.
A searchable image database using SigLIP 2 (CLIP) embeddings and SQLite-vec for efficient similarity search.
CLI RAG tool - index 30+ document formats, hybrid search, ask questions and get sourced answers.
Privacy-first local AI assistant for macOS (MLX + sqlite-vec) with 0.42s mean latency and <5% hallucination rate
Shared knowledge layer for human-agent teams. Agents search, classify, and manage knowledge alongside your team.
The AI agent memory engine that deliberately stays small. SQLite + sqlite-vec + Ollama, CJK-native, three entry points. Apache 2.0.
Local-first browser agent with long-term memory. Your browsing lives in a SQLite file you own — no cloud, no sync.
A local semantic emoji search engine that uses transformer embeddings and sqlite vector search to find the perfect emoji from natural language queries. Fast, offline, and powered by Streamlit.
Local-first paper research copilot for evidence-grounded QA, paper search, and generating verifiable new model-framework proposals from a user's research direction.
A local academic paper library exposed as Model Context Protocol tools. Find papers, locate passages, verify citations before you cite them.
Add a description, image, and links to the sqlite-vec topic page so that developers can more easily learn about it.
To associate your repository with the sqlite-vec topic, visit your repo's landing page and select "manage topics."