Vibe Coding Discoversupermemory
View on GitHubMemory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
Supermemory is a memory and context engine for AI: it extracts facts from conversations, maintains user profiles (~50ms), and serves hybrid RAG+memory search over one API. Self-hostable via one binary with local embeddings, plus MCP server and plugins for Claude Code, Cursor and other clients.
Use Cases
Persistent memory across Claude Code/Cursor sessionsAuto-maintained per-user profile injection into system promptsHybrid RAG + memory search over docs and personal contextSync Google Drive, Gmail, Notion, OneDrive, GitHub into a knowledge baseMulti-modal ingestion of PDFs, images, video and codeAdd memory to agents via a single API instead of custom vector pipelinesFully local/offline memory server behind OpenAI-compatible modelsFramework drop-in wrappers for AI SDK, LangChain, Mastra
Built With
- Language
- TypeScript
- Frameworks
- Vercel AI SDK · LangChain · LangGraph · OpenAI Agents SDK · Mastra · Agno · n8n · MCP · Drizzle ORM · Hono · Remix · Zod · Turbo · Bun · Cloudflare Workers
Tags
agent-memory · long-term-memory · rag · embeddings · hybrid-search · vector-search · user-profiles · mcp · context-engine · self-hosted · connectors · semantic-search · knowledge-base · llm · typescript · ollama