MCP server that lets your AI assistant remember everything about your home.

Stash is here to solve one of the biggest headaches in AI agent development — memory. If you've ever built an AI agent, you know the struggle: every conversation starts from scratch, context gets lost, and you end up stuffing giant prompts just to keep things coherent. Stash gives your agents a persistent memory layer backed by Postgres, so they can remember episodes, facts, and working context across sessions. Plus, it ships as a single self-hosted binary with an MCP server included — no cloud, no vendor lock-in, just pure dev-friendly tooling that actually works.

This MCP server transforms how developers interact with codebases by building a persistent knowledge graph that indexes repositories in milliseconds across 155 programming languages. With sub-millisecond query speeds and 99% token reduction, it enables AI coding assistants like Cursor, Claude Code, and Windsurf to understand your entire codebase context without drowning in context windows. Built as a single static binary with zero dependencies, it runs anywhere.

TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.

Persistent memory for any AI — MCP server, HTTP API, CLI. Works with Claude, ChatGPT, Grok, Gemini, Codex, Cursor, OpenClaw, and any MCP client. 97.8% R@5 on LongMemEval. Pure SQLite FTS5, zero cloud dependencies.