AI agents

Open-source AI agents

An AI agent is a program that uses a language model to decide what to do next, calls tools such as a browser, a code interpreter or an API, and repeats until the task is done. The projects here range from frameworks for building your own agents to finished agents that write code, browse the web or run business workflows.

How to choose

Compare three things. Which models it can use: a single provider, or any OpenAI-compatible endpoint including local ones. How it limits what the agent may do: sandboxing, approval steps and permission lists. And whether it keeps memory between steps and sessions. An agent that runs code or shell commands should run in a sandbox, so check that before giving it access to your machine.

Most-starred projects

1,657–1,680 of 4,275

NeoLabHQ

context-engineering-kit

★ 1,737

Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source alternative.

TypeScript

bespokelabsai

curator

★ 1,735

Synthetic data curation for post-training and structured data extraction

Python

Eynzof

Hermes-CN-Desktop

★ 1,735

Hermes Agent CN desktop app, Windows-First, built with Tauri, Typescript and Rust. Isolated Hermes Agent core insides.

TypeScript

pawurb

hotpath-rs

★ 1,735

Rust profiler for CPU, memory, SQL, HTTP, and async performance, with Prometheus and Grafana support.

Rust

BeaconBay

ck

★ 1,734

Local first semantic and hybrid BM25 grep / search tool for use by AI and humans!

Rust

Asymptote-Labs

agent-beacon

★ 1,729

Agent Beacon is the world's first open-source telemetry layer for AI agents wherever they run: locally, in CI, in the browser, or in the cloud.

px0-ai

px0

★ 1,729

px0 is a fast, lightweight, read-only IDE designed for instant code navigation and review in your browser. Booting in under 1 ms and using ~20 MB of RAM, it turns your browser into a zero-latency inspection console with symbol-level navigation, deep search, and syntax highlighting across massive codebases.

JavaScript

101dotxyz

GPTeam

★ 1,723

GPTeam: An open-source multi-agent simulation

Python

microsoft

edgeai-for-beginners

★ 1,723

This course is designed to guide beginners through the exciting world of Edge AI, covering fundamental concepts, popular models, inference techniques, device-specific applications, model optimization, and the development of intelligent Edge AI agents.

Jupyter Notebook

MorDavid

BruteForceAI

★ 1,721

Advanced LLM-powered brute-force tool combining AI intelligence with automated login attacks

Python

lahfir

agent-desktop

★ 1,719

Agent Desktop gives any agent reliable computer use on the desktop. Built with Rust, it sees any app's real UI structure through OS accessibility trees and operates it — refs stay stable and actions stay safe to retry, instead of guessing from pixels.

Rust

mithun50

openclaw-termux

★ 1,719

Run OpenClaw AI Gateway on Android — standalone Flutter app with built-in terminal, web dashboard, and one-tap setup. Also available as a Termux CLI package.

Dart

ai4s-research

open-science

★ 1,717

Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tauri + MCP + agent skills.

TypeScript

getnao

nao

★ 1,717

👾 nao is an open source analytics agent. (1) Create context with nao-core cli, (2) deploy nao chat interface for everyone

TypeScript

sendaifun

solana-agent-kit

★ 1,717

connect any ai agents to solana protocols

TypeScript

aklivity

zilla

★ 1,716

🦎 A lightweight, multi-protocol gateway for event-driven applications and AI agents. Expose and govern Kafka, MQTT, APIs, and MCP through one high-performance engine with shared routing, security, schema, and observability.

Java