AI/ML open-source repositories from GitHub Trending. Recommended ranking blends AI importance (60%) with star-growth popularity (40%).
Anti-AI-slop design skill for Claude Code, Cursor, and Codex.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients 逆向/渗透/安全技能路由包 - AI 自动路由 + 按需自举工具链 + 自动进化经验库 | 支持 Claude Code / Kiro / Cursor / Cline 等代码 AI 客户端
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
Agent skill that removes signs of AI-generated writing from text
Comprehensive production pipeline for quad-modal AI filmmaking with Seedance 2.0
Lightweight loop engineering state kernel for long-running AI agent teams. Agent-loop agnostic across Codex, Claude Code, and other coding agents, with durable goals, quota-aware auto-wake, executable todos, evidence logs, and verifiable handoffs.
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
Fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities
Universal SEO skill for Claude Code. 25 sub-skills + 18 sub-agents covering technical SEO, E-E-A-T, schema, GEO/AEO, backlinks, local SEO, maps intelligence, semantic clustering, e-commerce SEO, international SEO, Google APIs, and PDF/Excel reporting. Optional DataForSEO, Firecrawl, and Banana extensions.
The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero config.
A coding agent for open models like Kimi K3
The open-source alternative to Webflow, Framer and WordPress. Agentic self-hosted visual CMS outputting clean static pages. Users, roles, plugins, content, database, it's all there.
Lightweight coding agent that runs in your terminal
💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported.
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
🦔 PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP.
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
Open-source MCP to use Blender with any LLM
🎯 All you need. Nothing you don't. Open source project management that works for you, not against you.
A library of agent skills for CAD, CAE and CAM
The open-source alternative to Claude Cowork (powered by opencode)
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
SGLang is a high-performance serving framework for large language models and multimodal models.
A framework for building realtime voice AI agents 🤖🎙️📹
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
A collection of DESIGN.md files analysis by popular brand design systems. Drop one into your project and let coding agents generate a matching UI.
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.
把书、长视频、播客等高价值内容蒸馏成可执行的 Agent Skills
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
An AI-boost cross-platform multi-protocol fluent-design concurrent downloader built with Python & Qt.
Graph-Native Infrastructure for Context and Accountable AI Systems
A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claude Code, Cursor.
A utility-first CSS framework for rapid UI development.
Framework for evaluating and improving agents
🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine
Apache Ossie, industry wide specification effort to standardize how we exchange semantic metadata across analytics, AI and BI platforms, providing a vendor neutral, single source of truth for semantic data
Python Data Science Handbook: full text in Jupyter Notebooks
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
CLI tool for configuring and monitoring Claude Code
No fortress, purely open ground. OpenManus is Coming.
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Lightweight, open-source AI agent for your tools, chats, and workflows.
Why is this running? Trace any process, port, container, or file back to what started it - CLI + TUI.
A simple tool for coordinating several AI agents.
Build your own AI SRE agents. The open source toolkit for the AI era.
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.
[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)
Summer 2026 software engineering, data science, AI, quant, product management, and hardware internship postings. Updated daily by Simplify and Pitt CSC.
🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
[🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs:https://ufund-me.github.io/Qbot✨ :news: qbot-mini:https://github.com/Charmve/iQuant
Free, open-source web app for learning about ontologies and Microsoft Fabric IQ. Explore a catalogue of pre-built ontologies, design your own visually, export as RDF/XML, and share interactive diagrams. Zero backend, fully static.
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
AIscikit-learn is a widely-used open-source machine learning library for Python, offering algorithms for classification, regression, and clustering. It provides a simple API and consistent interface to streamline workflows from data preprocessing to model evaluation.
Easily train a good VC model with voice data <= 10 mins!
Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.
AIA high-performance MCP server that indexes codebases into a knowledge graph, processing average repos in milliseconds. It supports 158 languages, sub-millisecond queries, and 99% fewer tokens.
AIStrix is an autonomous AI penetration testing tool that dynamically runs your application to find vulnerabilities and validates them with real proof-of-concepts. It integrates with GitHub Actions and CI/CD pipelines to automatically block insecure code before it reaches production.
AIThis tool enables Claude to directly 'watch' and analyze videos from various sources like YouTube. It automates video downloading, frame extraction, and caption/audio transcription to provide the content to Claude.
AIAirLLM is an open-source library that enables inference of 70B-class large language models on a single 4GB GPU without quantization or distillation. It can also run 405B Llama3.1 with 8GB VRAM, and supports CPU inference as well as 8-bit/4-bit quantization.
AISkillOpt is a text-space optimizer that treats an LLM agent's natural language skill document as a trainable parameter. It iteratively improves skills through trajectory-driven edits and validation-gated updates, producing deployable skill artifacts without modifying the underlying model weights.
AIWebwright provides LLMs with a terminal environment to launch multiple browser sessions and complete web tasks. It manages persistent state through code and logs rather than browser sessions, enabling efficient handling of complex web workflows.
AISANA is an efficiency-oriented codebase for high-resolution image and video generation using linear diffusion transformers. It has been accepted at multiple conferences including ICLR 2025 Oral and provides complete training and inference pipelines.
AIThis tool provides a CLI and skill set that equips coding assistants with the expertise to create, evaluate, deploy, and manage AI agents on Google Cloud. It integrates with various coding agents like Claude Code and Codex to support the building of enterprise-grade agents.
AIslime is an LLM post-training framework for RL scaling that connects Megatron and SGLang for high-performance training and flexible data generation. It is a battle-tested, lightweight framework validated through complete training loops for SOTA-level models like the GLM series.
AIEagle is a family of frontier vision-language models from NVIDIA that explores data-centric strategies for general-purpose multimodal understanding, long-context reasoning, and embodied applications. It has been adopted as a core backbone for major NVIDIA initiatives like GR00T robotics and Nemotron, demonstrating real-world industrial applicability.
AIOpenCV is an open-source library for computer vision and machine learning. Written in C++, it supports various languages including Python and Java.
AIAnsible is an agentless IT automation platform that uses SSH and playbooks for configuration management, application deployment, and cloud provisioning. It describes infrastructure in a plain-English-like YAML syntax, enabling a low learning curve and parallel management.
AIMiniCPM-V 4.6, with 1.3B parameters, outperforms larger models like Gemma4-E2B-it and achieves about 1.5x higher token throughput than Qwen3.5-0.8B. Its novel intra-ViT early compression technique reduces visual encoding cost by over 50%, and supports mixed 4x/16x visual token compression rates, enabling deployment on mobile platforms such as iOS, Android, and HarmonyOS.
AIThis official AWS toolkit provides MCP servers, skills, and plugins to help AI coding agents build, deploy, and manage applications on AWS. It is compatible with agents like Claude Code, Codex, Cursor, and Kiro, supporting workflows from service selection to deployment.
AINVIDIA Cosmos is an open platform providing world models, datasets, and tools for developing Physical AI for robots, autonomous vehicles, and more. The Cosmos 3 model family is an omnimodal world model that integrates language, image, video, audio, and action sequences, supporting two runtimes: Reasoner and Generator.