
Private on-device AI assistant for chatting with documents, with local models
- Free
- Open-source agent
- 68.4K GitHub stars
- Personal assistants

Private on-device AI assistant for chatting with documents, with local models
Local-first Markdown vault memory and semantic search for AI coding assistants
Searches your own code, PDFs and Office files and returns exact source citations
Runs locallyIndex code, docs, PDFs and data in a local SQLite file and serve context to agents
Runs locallySelf-hosted MCP server: shared agent memory, document search and a code index
Not checked yetLocal code and document search for AI agents, with an optional paid cloud index
Runs locallyLocal-first RAG that answers from your documents with page and section citations
Runs locally
Run Helix queries on Helix Cloud and read query insights, health and database settings
Not checked yetShared long-term memory that Claude, ChatGPT, Cursor and other MCP agents use together
Not checked yetLocal-first memory for agents that cites sources and says when it doesn't know
Runs locallyAgent memory in SQLite or Postgres that flags stale facts and abstains when unsure
Runs locallyTurn folders, repos, Notion and Confluence into one searchable MCP endpoint per project
Not checked yetContext control plane that picks the most useful retrieved passages under a token budget
Runs locallyShared long-term memory and knowledge graph for AI agents, with citations and self-hosting
Not checked yetOn-premises document retrieval for agents, with folder-level access rules checked first
Runs locallyLocal encrypted memory for agents with hybrid recall and key-destroying erasure
Runs locally