AI & Machine Learning

obra

superpowers

★ 292,440

Superpowers packages repeatable engineering practices as agent skills, covering design, planning, testing, debugging, review, and branch completion.

mattpocock

skills

★ 271,943

This repository collects Matt Pocock's reusable agent skills for TypeScript, testing, debugging, and day-to-day software work.

affaan-m

ECC

★ 269,495

ECC supplies agent skills, security checks, memory patterns, and research workflows aimed at reducing wasted context during coding sessions.

NousResearch

hermes-agent

★ 249,187

Hermes Agent runs as a personal agent with persistent memory, scheduled work, tool use, and integrations for messaging and local services.

tensorflow

tensorflow

★ 200,623

TensorFlow supplies the tools to build, train, and deploy machine-learning models across servers, browsers, and edge devices.

Significant-Gravitas

AutoGPT

★ 187,586

Open-source platform for building and running AI agents that complete full workflows, defined in plain English or a visual builder and run on demand or on a schedule.

firecrawl

firecrawl

★ 186,493

The API to search, scrape, and interact with the web at scale. 🔥

ollama

ollama

★ 181,861

Run leading open models locally with a simple developer experience.

anthropics

skills

★ 178,978

Anthropic's public collection of Agent Skills — folders of instructions, scripts, and resources Claude loads dynamically to perform specialized tasks repeatably.

huggingface

transformers

★ 166,652

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

langgenius

dify

★ 157,512

Dify is an open-source LLM app platform combining agentic workflows, RAG pipelines and model management, deployable on cloud, VPC, or self-hosted infrastructure.

msitarzewski

agency-agents

★ 155,291

Agency Agents provides role-specific agent definitions and working procedures for engineering, design, marketing, product, and community tasks.

open-webui

open-webui

★ 153,167

Open WebUI is a self-hosted AI interface that runs entirely offline, supporting Ollama and OpenAI-compatible APIs with a built-in inference engine for RAG.

anthropics

claude-code

★ 148,319

Claude Code is an agentic coding tool that lives in your terminal, executing routine tasks, explaining complex code, and handling git workflows via natural language.

DietrichGebert

ponytail

★ 147,444

Ponytail adds YAGNI-focused review instructions that push coding agents to remove unnecessary abstractions and avoid speculative code.

langchain-ai

langchain

★ 147,049

LangChain gives agent builders a common layer for models, tools, retrieval, and multi-step execution.

github

spec-kit

★ 139,409

Toolkit to help you get started with Spec-Driven Development. Spec Kit Define what to build before building it, with any AI coding agent.

farion1231

cc-switch

★ 138,617

CC Switch manages providers, models, prompts, MCP servers, and local settings for several coding assistants from one desktop app.

Comfy-Org

ComfyUI

★ 134,951

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

nextlevelbuilder

ui-ux-pro-max-skill

★ 131,522

UI UX Pro Max gives coding agents searchable design guidance for layouts, color, typography, components, and platform-specific interface work.