# Top Open Source AI Projects
6,260 listed projects across 66 scenarios — 100+ popular tags for filtering; ranked by inclusion criteria and public GitHub metrics.
Last updated:
| Rank | Project | Scenario | Stars | Forks | Updated | License |
|---|---|---|---|---|---|---|
| 41 |
MoneyPrinterTurbo
Generate HD short videos from a topic or keyword with an automated AI workflow. |
Video & Animation | 118.5K | 18.1K | 08/28/26 | MIT |
| 42 |
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs |
Inference & Local Deploy | 90.4K | 21.4K | 08/29/26 | Apache-2.0 |
| 43 |
ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. |
AI Coding Assistants | 116.4K | 6.3K | 08/07/26 | MIT |
| 44 |
browser-use
🌐 Make websites accessible for AI agents. Automate tasks online with ease. |
AI Agents & Automation | 111.7K | 12.3K | 08/29/26 | MIT |
| 45 |
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store. |
AI Coding Assistants | 112.3K | 10.9K | 08/29/26 | Apache-2.0 |
| 46 |
gemini-cli
An open-source AI agent that brings the power of Gemini directly into your terminal. |
AI Agents & Automation | 106.7K | 14.5K | 08/29/26 | Apache-2.0 |
| 47 |
opencv
Open Source Computer Vision Library |
Computer Vision | 90.6K | 57.0K | 08/29/26 | Apache-2.0 |
| 48 |
awesome-design-md
AI Tool Directories & Curated Lists 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. |
AI Tool Directories & Curated Lists | 111.2K | 12.7K | 07/31/26 | MIT |
| 49 |
LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step |
Education & Research | 104.0K | 15.9K | 08/29/26 | Other |
| 50 |
caveman
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman |
AI Coding Assistants | 101.8K | 5.9K | 08/29/26 | Other |
| 51 |
playwright
Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API. |
AI Agents & Automation | 95.3K | 6.4K | 08/29/26 | Apache-2.0 |
| 52 |
pi
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI |
AI Coding Assistants | 99.1K | 12.3K | 08/29/26 | MIT |
| 53 |
TradingAgents
TradingAgents: Multi-Agents LLM Financial Trading Framework |
AI Agents & Automation | 101.7K | 19.5K | 07/18/26 | Apache-2.0 |
| 54 |
Deep-Live-Cam
real time face swap and one-click video deepfake with only a single image |
Video & Animation | 96.2K | 14.0K | 08/29/26 | AGPL-3.0 |
| 55 |
open-design
Open-source Claude Design alternative: local-first desktop app turning coding agents into a design engine for prototypes, landing pages, dashboards, slides, images, and video, with file exports (HTML, PDF, PPTX, MP4). |
AI Design & Prototyping | 92.6K | 10.7K | 08/29/26 | Apache-2.0 |
| 56 |
ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs |
Knowledge Base & RAG | 89.6K | 10.6K | 08/29/26 | Apache-2.0 |
| 57 |
scikit-learn
Classical Machine Learning Frameworks scikit-learn: machine learning in Python |
Classical Machine Learning Frameworks | 67.1K | 27.3K | 08/28/26 | BSD-3-Clause |
| 58 |
claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More |
AI Agents & Automation | 92.6K | 8.1K | 08/29/26 | Apache-2.0 |
| 59 |
manim
Animation engine for explanatory math videos |
Video & Animation | 92.2K | 7.6K | 08/18/26 | MIT |
| 60 |
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video. |
Computer Vision | 92.0K | 12.2K | 08/29/26 | MIT |
Frequently Asked Questions
Here are answers to some common questions. If you have other questions, please feel free to contact us.