sqlite-vec

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

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

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

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

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.

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.

Shared memory for Claude Code, Codex, and Cursor. Your agent recalls decisions from weeks ago — including what the other engines worked out. Local semantic search over all three histories, as MCP tools.

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, 13-tool Python MCP + 17-tool BrainBar surface with ToolAnnotations

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

∿ Py-Agent · Local-First & Private CLI Harness with Pi, Claude, and Hermes profiles, llama.cpp backend, and in-memory NOOA IPython Kernel.

Локальная мульти-агентная система на self-hosted LLM (Ollama). 3 канала (Telegram/консоль/MAX), 4 типа моделей (LLM/embed/vision/voice), мультимодальность (текст/PDF/фото/голос), роли Planner/Executor/Critic с рефлексией. Инструменты: почта, Яндекс.Диск, web, OCR, cron-планировщик. Семантическая память (sqlite-vec). Coverage 88%. Без облачных API.

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.

Self-hosted, self-learning, provider-agnostic personal agent kernel. Local-first memory in one SQLite database, project-scoped, reachable from any tool over MCP or a CLI.

Git-native, semantically-searchable memory storage for Claude Code. Captures decisions, learnings, and context as git notes with vector search.

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

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.

Local semantic search over your AI coding agent session transcripts, using Ollama embeddings and sqlite-vec