Lists (1)
Starred repositories
36
stars
written in Python
Clear filter
分享 GitHub 上有趣、入门级的开源项目。Share interesting, entry-level open source projects on GitHub.
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero
SGLang is a fast serving framework for large language models and vision language models.
📺IPTV直播源自动更新平台『🤖全自动采集、筛选、测速、生成流程🚀』：每日更新两次，提供免费结果订阅，输入播放器即可观看；频道自定义；个性化配置；订阅源/组播源/酒店源/本地源；IPv4/IPv6；接口验效；推流；工作流、Docker、命令行、GUI多端部署 | IPTV live streaming source automatic update platform
<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
A list of free LLM inference resources accessible via API.
强国通 科技强国 学习强国 xuexiqiangguo 全网最好用开源网页学习强国助手：TechXueXi （懒人刷分工具 自动学习）技术强国，支持答题，支持 docker 45分/天
One-stop Proxies Crawling and Aggregation Platform
WiFi密码暴力破解工具-图形界面，支持WPA/WPA2/WPA3、多开并发、自动破解、自定义密码本、自动生成密码字典
📊 Simple package for monitoring and control your NVIDIA Jetson [Orin, Xavier, Nano, TX] series
In order to make it easier to use the ComfyUI, I have made some optimizations and integrations to some commonly used nodes.
Expose your TCP/UDP port behind full-cone NAT to the Internet.
PDF2zh for Zotero | Zotero PDF中文翻译插件
Home Assistant integration for Haier hOn: support for Haier/Candy/Hoover home appliances like washing machines and air conditioners in 28 languages.
✨ Reverse-engineered Python API for Google Gemini web app
A generic and extendable WebDAV server based on WSGI
Web-based Gemini models wrapped into an OpenAI-compatible API.
DeepSeek OCR WebUI for fast standalone operation