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.
12+ built-in tools with a sandboxed execution pipeline. File read/write, shell commands, web search, symlink protection, per-tool timeouts, and a 6-policy permission system.
A Claude Code-style terminal chat with 15+ slash commands, persistent sessions, and an autonomous CEO/Worker task loop. Permission prompts surface inline — no need to leave the terminal.
A chief model plans the task, 8 specialist roles execute in parallel, and the chief synthesizes the result. Assign different models per role — Claude for reasoning, Gemini for speed.
OpenAI, Gemini, Claude, Grok, Groq, OpenRouter, Ollama, OpenCode Zen, OpenCode Go, and Kilo Code — with automatic fallback chain and a free/paid model browser for the gateway providers. Switch mid-conversation with /model. API keys encrypted with AES-256-GCM.
Fully managed server lifecycle: auto-download, GPU offloading (NVIDIA/AMD/Metal), VRAM detection. No Docker, no terminal — everything from one native desktop app.
QR pairing with whatsmeow. Read, search, and reply to messages. Message yourself and Memo answers as a full assistant — chat, memory, and agent tools, no need to open the app. Everything stays local.
Connect a bot token and talk to Memo the same way you would on WhatsApp — an owner lock means only you get a reply. Create, list, or cancel a routine straight from the conversation.
E2E-encrypted Google Drive sync (AES-256-GCM, PBKDF2). Auto-sync every N messages. Full .memo archive export. Double-confirm wipe. Your data is encrypted before it leaves your machine.
Thin Flutter companion for Android/iOS over LAN or built-in ngrok tunnel. Built-in Tailscale tunnel for private networking. Access your brain from anywhere with token auth.
Schedule anything Memo should do on its own, in plain language — as a simple prompt or a full tool-using agent run. Now creatable, listable, and cancellable straight from a WhatsApp or Telegram conversation, not just the Routines tab.
On by default. Memo notices habits you mention or repeat and gently brings them up — woven into a normal reply or as a suggestion banner. Fully off under Incognito and configurable per-layer under Minimal Mode.
A local Anthropic- and OpenAI-compatible endpoint — point Claude Code or any OpenAI-shaped tool at Memo and it runs your local model or your own provider key behind the scenes, full tool calling included.
Pool several PCs' compute to run one GGUF model too large for any single machine — one Host keeps the file, others join and lend RAM/VRAM over the network via llama.cpp's rpc-server.
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.