AI & MCP
AI that actually knows your tasks
Todo doesn't just store — it indexes, understands and answers. Vector search, LLM-sourced answers, and a native MCP server for your agents.
Semantic search & Ask
Vector search
Tasks, descriptions, attachments and notes indexed in PostgreSQL + pgvector.
Ask (RAG)
A natural-language question, an answer written by an LLM — with the exact sources.
Transparency
Every AI call is logged: model, prompt, input and output tokens.
The LLM of your choice
Todo isn't tied to any provider. Pick your provider and model in settings — the list of available models is fetched live.
Multiple providers
Switch between the major LLM providers, without touching code.
Custom model
Pick a model from the list, or type the id of a custom one.
Your key, your credits
Bring your own API key when self-hosted; on Cloud, AI is included via credits.
Pluggable embeddings
Stay fully offline, or plug in a premium embedding provider. It's a single environment variable.
Local
all-MiniLM-L6-v2 (384 dim). Offline, no API key, your data never leaves the server.
Voyage
voyage-3 (1024 dim). Higher-quality embeddings via VOYAGE_API_KEY.
OpenAI
text-embedding-3-small (1536 dim) via OPENAI_API_KEY.
Model Context Protocol
Your tasks become tools for AI
Todo ships an MCP server (streamable HTTP + stdio). Any compatible LLM agent can create, search and update your tasks directly — securely, via a scoped API key.
Remote agents? An OAuth 2.1 authorization server secures hosted MCP connectors — managed right from your settings.
Connect any MCP client
Works with any client or agent that speaks the Model Context Protocol. API keys carry the mlt_ prefix and can be revoked at any time.
Give your AI a real task manager
Semantic search, sourced answers and agentic access via MCP — all on your own infrastructure, with the LLM of your choice.