
Fully local voice-enabled AI assistant that browses the web, codes and plans tasks
- Open source
- Open-source agent
- 27.7K GitHub stars
- Personal assistants

Fully local voice-enabled AI assistant that browses the web, codes and plans tasks

Self-hosted multi-agent system that plans and runs penetration tests in a sandbox

Open-source Python framework for building production RAG pipelines and agents

Open protocol letting AI agents from different frameworks discover and work together

SDK for browser agents with Playwright-style API and self-healing actions

Open-source research agent that writes cited reports from the web and your documents

Open-source enterprise agent platform with RAG knowledge bases and workflows

Rust-built terminal coding agent for running many agents in parallel

Type-safe Python framework for building agents and LLM applications

Project-based course on making AI coding agents reliable through harness design

Platform for stateful agents that learn from experience, with an open-source CLI harness

Open-source TypeScript framework and personal agent for autonomous AI agents
Unified customer service inbox with AI agents for WhatsApp, Instagram, Facebook and email

Skill-based research workflow where one model drives and another reviews, overnight

Open-source generative UI framework letting agents render native interfaces

Open-source desktop multi-agent workspace that can control browser and apps

Run many coding agents in parallel, each on its own branch, with PR and CI feedback loops

Rust agent operating system with scheduled autonomous Hands and a WASM sandbox

Chrome and Edge extension where an AI agent works in your signed-in browser

Multi-language framework for production AI agents and multi-agent workflows

Minimal self-evolving agent framework of about 3K lines that controls a computer

Multi-agent system modelled on an imperial court, with review steps and a dashboard

Self-hosted AI trading stack: research, strategy code, backtests, paper and live trading

Meta-harness that runs, governs and shares sessions across coding agents

Open-source runtime where a queen agent builds colonies of parallel workers

Run a pixel-art office of coding agents on subscriptions you already pay for

Strands toolkit with a ready agent harness, sandbox and evals in Python and TypeScript

Self-hosted crew of AI agents on an org chart with shared graph memory

100-line minimalist LLM framework built on a graph and shared store

Java agent framework built on Spring AI with DAG graphs and a visual studio