Memo is a private, local-first AI second brain. It runs models locally, remembers everything in a vector store, and never phones home. Chat through external APIs when you need more power, or stay 100% offline — your call.
one-click installer · llama.cpp bundled · no terminal required
Zero telemetry, no training on your chats, no cloud dependency. Optional encrypted backup only if you turn it on.
Every interaction is embedded and indexed in a local vector store. Relevant context is retrieved automatically on each turn.
Run chat through a powerful external API while a tiny local model handles embeddings — or stay 100% offline. Your call, per model.
A real Flutter desktop app on Windows, Linux, and macOS, with a mobile companion. It feels like software you own.
This isn't a video — it's Memo's memory pipeline replayed live, right on the page.
A real RAG memory and a tool-calling agent, paired with an interface a first-time user can navigate.
SQLite + sqlite-vec vector search. Every interaction is semantically indexed for O(log n) retrieval. Cross-mode: use a cloud AI for chat while a local model handles embeddings.
27 built-in tools with a sandboxed execution pipeline, up to 40 iterations per turn. File read/write/edit, shell commands, web search and page-fetch, a `change_directory` tool to reach files outside Memo's folder, per-tool timeouts, and a policy-based permission system.
Three gears, cycled with Ctrl+Tab instead of one on/off switch. Plan investigates and writes a saved plan without touching a file, then asks in chat whether to proceed. Auto confirms edits as before. Build runs edits and commands without waiting. Auto-permission chains a finished plan straight into Build, in the same reply.
Hand Memo a `Task.md` checklist and walk away. Worker mode runs each item as its own turn; planner/executor mode plans first and waits for your approval. Up to 3 sub-agents split a large item — one coder, up to 3 parallel read-only reviewers. A busy chat queues instead of dying, a rate limit pauses and resumes from the exact item it was on, and every terminal state notifies you by chat and push.
A small always-on-top character, its own window sharing the same running app, that reflects what Memo is doing right now across chat, WhatsApp, Telegram, and the task loop — thinking, writing, running a named tool, or celebrating a finished turn. Two selectable skins, idle animation, genuinely always-on-top even on Wayland.
Memo adapts to how you work — whether you are shipping code, writing a thesis, or just want an AI that respects your privacy.
Drop in your codebase. Ask the agent to refactor modules, write tests, or explain a complex function. Orchestra mode splits work across specialist models — one writes React, another writes Go. All offline.
Upload papers, notes, and references. RAG memory connects ideas across weeks of work. Ask "what was that citation about reinforcement learning?" and get the exact paragraph — no keyword search needed.
Your conversations, files, and memories never leave your machine. No account, no cloud dependency. Use external APIs when you need more power — keys are AES-256 encrypted on disk. You hold all the cards.
One click installs Memo with llama.cpp bundled. Open the app, pick a model from Discover, and start chatting.
Memo is open source. Inspect the code, self-host, or contribute on GitHub.
Server-only installers, Docker/CasaOS images, a 4-mode auth system, and full SSH management via the memo CLI — new as of v3.5.5.