Open-source AI agents

Microck

ordinary-claude-skills

★ 413

An unappealing collection of Claude Skills and resources.

millionco

cli-to-js

★ 413

Turn any CLI into a JavaScript API

smart-mcp-proxy

mcpproxy-go

★ 413

Supercharge AI Agents, Safely

syswonder

robonix

★ 413

The Agentic Operating System for Robots

mezmo

aura

★ 412

AURA is a production-tested SRE agent platform you can deploy in minutes. AURA handles the guardrails, APIs, state management, streaming, and failure handling required to put AI to work safely on production infrastructure.

microsoft

iq-series

★ 412

The IQ Series is a hands-on learning experience for Microsoft IQ: Microsoft's unified intelligence layer for the enterprise, spanning Foundry IQ, Work IQ, and Fabric IQ. The series includes video episodes, Jupyter notebooks, and Azure deployment templates.

ohdearquant

lionagi

★ 412

An intelligence orchestra

TheDesignFounder

DreamLayer-Eval

★ 412

DreamLayer Eval: open-source benchmarking for image and video diffusion models. Automate prompts, seeds, and metrics for reproducible results. A research project from DreamLayer AI (dreamlayer.io).

wesammustafa

opencode-primer

★ 412

Master OpenCode, the open-source AI coding agent — setup, agents, skills, plugins, MCP, Zen & headless CI.

GizClaw

flowcraft

★ 411

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.

Runchuan-BU

BioClaw

★ 411

AI-Powered Bioinformatics Research Assistant. Built on OpenClaw.

aws-devtools-labs

aws-blocks

★ 410

Composable building blocks for full-stack AWS apps — define infrastructure and runtime code together with end-to-end type safety using TypeScript, local mocking, and native client codegen for Kotlin, Swift, and Dart.

earthtojake

step.parts

★ 410

12,000+ open source STEP parts for your next CAD project

shamspias

customizable-gpt-chatbot

★ 410

Veldra — talk an agent into existence, then watch it grow. A self-hostable, local-first agent platform: describe what you need in plain language and it compiles a working agent tools, MCP, RAG, teams. The more you use it, the better it gets agents learn from your feedback and reshape as you talk.

weibocom

rill-flow

★ 410

Rill Flow is a high-performance, scalable workflow orchestration engine for distributed workloads and LLMs

Meridiona

meridian

★ 409

Stop letting your work go unnoticed. Meridian keeps an automatic work journal of what you worked on and what you finished, summarised daily, and automatically drafts your project tickets for you.

sonichi

sutando

★ 409

My AI Stand. Realtime by day, rewriting itself by night. Summon my AI superpower.

AmrDab

clawdcursor

★ 408

clawdcursor compiles whatever's on screen into one UI map — accessibility tree and OCR fused into stable, addressable elements, with a screenshot only when needed — then drives apps through reusable scripts, verifying every action and routing it through a single safety gate.

binghe001

BingheGuide

★ 408

A technical knowledge base distilled from the author Binghe's years working as a developer and architect at major internet companies, offering a clear, detailed learning tutorial focused on AI, agents, AI projects, core Java and Go content, underlying principles, architecture, and penetration techniques.

canyonroad

agentsh

★ 408

Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.

craftzdog

tmux-claude-hatch

★ 408

tmux plugin that runs Claude Code sessions in popups per project directory, with an fzf picker showing each session's status and a bell that highlights the window that needs you.

evilmartians

agent-prism

★ 408

React components for visualizing traces from AI agents

langchain-ai

langchain-google

★ 408

🦜🔗 LangChain interfaces to Google's suite of AI products (e.g. Gemini & Vertex AI)

MAX-API-Next

MAX-API

★ 408

MAX API Next is a research-driven community of AGI enthusiasts from universities and research institutes, focused on governance of AI models and agents and on open infrastructure for the AGI era, covering multi-model and multi-platform access, continuous support for domestic Chinese models, AgentOps practice, cost auditing, permissions and security boundaries, and private deployment.