AI open source rankings.

A universal Dear ImGui hook for DirectX 12/11/10/9, OpenGL, and Vulkan. Compatible with Windows, Linux, and Steam Deck, featuring integrated MCP via a NamedPipe for game debugging and control.

text classification - no machine learning knowledge needed

Implementation of PoseNet

Sample Generative AI tool for evaluating Infrastructure as Code and architecture diagrams against AWS Well-Architected best practices.

🏔️ The AI-native RSS reader

30 秒找到真正适合你的 DeepSeek Harness插件。每天自动抓取 GitHub 上的 `dsh-plugin` 项目并逐个复核：真实插件分类收录，蹭标签项目剔除。通过场景化分类、精选推荐、热度排行和图文导览，帮你快速看懂每个插件能做什么、适合谁，以及如何开始使用。欢迎 Star ，让好用的插件更快被发现。

MCP server enabling AI agents to interact with Flutter apps at runtime - let them inspect widgets, simulate taps, enter text, scroll, and take screenshots.

Easy whole-brain modeling for computational neuroscientists 🧠💻👩🏿‍🔬

Provide OpenAI style API for ChatGLM-6B and Chinese Embeddings Model

A project to make Amazon Echo respond to sign language using your webcam

code released for our ICML 2020 paper "Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation"

Deepfakes Software For All

TensorFlow code and pre-trained models for BERT

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

🥇掘金翻译计划，可能是世界最大最好的英译中技术社区，最懂读者和译者的翻译平台：

Let us control diffusion models!

The first real AI developer

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

用 Express 和 Vue3 搭建的 ChatGPT 演示网页

Open-Sora: Democratizing Efficient Video Production for All

If you want to become good at AI engineering & system design, join this newsletter 👇

Deezer source separation library including pretrained models.

An autonomous agent for deep financial research

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

基于 ChatGPT API 的划词翻译浏览器插件和跨平台桌面端应用 - Browser extension and cross-platform desktop application for translation based on ChatGPT API.

🤖 Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained

CVPR 2026 论文和开源项目合集