New Generation

[ECCV 2024] codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!

MyContext is a local-first desktop app for everyday communication and knowledge work

Open-source media server with a web interface and desktop app for anime and manga.

Turn GitHub Copilot into OpenAI/Anthropic API compatible server. Usable with Claude Code!

ChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.

Post-training with Tinker

cliamp - Terminal music player inspired by winamp

Stay on top of trending topics on social media and the web with AI

[WIP] Layer Diffusion for WebUI (via Forge)

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

AI-powered penetration testing assistant using local LLM on linux (Parrot OS)

OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871

A list of AI agents and robots to block.

一个持续更新的中文敏感词库，帮助开发者和内容审核者快速识别并过滤不当文本，即将迎来重大更新

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

轻量化 docker 可视化管理面板。lightweight panel for docker

跨平台微信小程序反编译 GUI 工具，.wxapkg 文件扫描 + 解密 + 解包工具

CSGHub is a brand-new open-source platform for managing LLMs, developed by the OpenCSG team. It offers both open-source and on-premise/SaaS solutions, with features comparable to Hugging Face. Gain full control over the lifecycle of LLMs, datasets, and agents, with Python SDK compatibility with Hugging Face. Join us! ⭐️

Renovation Engine for DirectX Games

Harness LLMs with Multi-Agent Programming

Skills for the Gemini API, SDK and model/agent interactions

Qwen3.8 is the large language model series developed by Qwen team, Alibaba Group.

🔍 导出并模糊搜索 Telegram 聊天记录 | Export and fuzzy search your Telegram chat history

一个基于 Next.js 16 构建的现代化视频聚合播放平台。采用独特的 "Liquid Glass" 设计语言，提供流畅的视觉体验和强大的视频搜索功能。

Running a big model on a small laptop

Language model tokenization at GB/s

A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.