sqlite-vec

Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.

The memory substrate for AI agents and developer tools. Git-versioned, file-native, MCP-first.

Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.

Your coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Cursor & any MCP client: Markdown source of truth, hybrid search (MLX/CPU + sqlite-vec), time-machine, contradiction radar, nightly self-optimization. No cloud, no keys.

Persistent memory MCP for AI agents — SQLite, knowledge graph, 13-tool Python MCP + 17-tool BrainBar surface with ToolAnnotations

Personal Telegram knowledge base — forward anything, search via DM. Hybrid SQLite + FTS5 + vector + voice, MCP server for Claude.

🧠 Mnema — Long-term memory for AI via MCP × Vector DB. Pluggable backends, hybrid search, Auto Dream consolidation, CLI + REST API + SDK.

Robot Memory - Persistent memory system for AI robots. MCP Server + hybrid search + spatial retrieval.

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.

SeekLink — hybrid semantic search for markdown vaults. Four-channel RRF fusion, MLX reranker, native CJK support. Fully local.

Local AI search engine for your files and agents — hybrid BM25 + vector semantic search (RAG) in one SQLite file. Millisecond queries, CPU-only, offline, no LLM in the query path.

CLI RAG tool - index 30+ document formats, hybrid search, ask questions and get sourced answers.

Persistent memory for Claude Code — invisible self-annotating metadata, semantic search, cross-project retrieval

A local academic paper library exposed as Model Context Protocol tools. Find papers, locate passages, verify citations before you cite them.

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.

The AI agent memory engine that deliberately stays small. SQLite + sqlite-vec + Ollama, CJK-native, three entry points. Apache 2.0.

Self-hosted memory for LLM agents - one SQLite file, zero services, MIT. Hybrid retrieval (FTS5 + sqlite-vec + RRF) with pain-weighted salience and a knowledge graph. Under matched embeddings, outperforms Mem0 on LoCoMo and LongMemEval. Your data, your provider, your disk.

Shared knowledge layer for human-agent teams. Agents search, classify, and manage knowledge alongside your team.

Local-first knowledge-graph memory layer for AI agents — what Mem0 charges for: 4-way RRF + L2 maintenance + bilingual classifier, one local SQLite. usearch f16 runs it on $10/year VPS.