
Private on-device AI assistant for chatting with documents, with local models
- Free
- Open-source agent
- 68.3K GitHub stars
- Personal assistants

Private on-device AI assistant for chatting with documents, with local models

Long-term memory layer for AI agents that stores typed facts and consolidates beliefs

Front-end quality checklist of 350+ rules, usable by people and AI tools via MCP

Distributed SQL database with vector search and transactions for AI workloads

Vectorless RAG engine that finds answers by reasoning over a document's page tree

Open-source knowledge framework for RAG Q&A, agent tasks and auto-built wikis

Toolkit layer that gives agents authenticated access to 1,000+ apps via SDK, CLI or MCP

Open-source shared memory hub that gives agent teams common conversation and code memory

Open-source AI gateway in Go that routes LLM calls with budgets, fallbacks and MCP

Microsoft toolkit for policy enforcement, identity and audit of autonomous agents

Python library that optimises prompts and code with reflective evolutionary search

Open-source gateway adding identity, policy and audit between AI agents and your systems

Ruby library with one API for 23 AI providers, tools and Rails conventions

Research router that decides whether a running task continues, recruits help or hands off

Browser engine and CLI built for agents that browse, extract and crawl at scale

TypeScript SDK implementing Hashgraph Consensus Standards from HOL