Lists (4)
Starred repositories
⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Factory / ms-swift / U…
Causal Discovery in Python. Learning causality from data.
Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu/Lark, DingTalk, Slack, Telegram, Discord, LINE, WeChat Work). Chat with your AI dev assistant f…
RuiC-PoseAtlas｜姿态 + 衣装双图鉴：288 组人体姿态 × 5 视角 × 1,439 张人台线稿，加 1,407 套无人物衣装 × 8 分类 × 86 个三语标签。中/英/日切换、搜索筛选、键盘浏览、原图下载，纯静态零依赖。
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06
Bring your Auday memories and recordings into your AI workflows.
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
WordCraft: an open-source, clean-room word processor in pure Rust
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Reverse engineer anything with agents, from app behavior down to native binaries.
一句话让 AI 帮你做产品宣传片！把产品名或网址告诉 Cursor、Claude Code、Codex 等 AI 编程工具，它会自己调研产品、画出多种风格样图让你挑选、截取 4K 真实页面、按音乐节拍卡点剪辑、生成 AI 旁白并逐句转写校验、自动审图，最后交付一支 4K 商业宣传视频和可在线播放的网页版。App、网站、SaaS、开源项目、课程、AI 模型都能做，你只需确认需求、试听配乐。不用…
基于 ESP32-S3 + TinyML 的魔杖。挥动魔杖即可触发魔法效果，支持手势识别、低功耗待机、个性化模型训练，软硬件全开源。
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
高性价比人生指南: 长寿防病、急救、省钱理财、法律红线、失业与工伤、医保社保、恋爱婚育、怀孕育儿、创业与做平台合规、出国与技能。每条写明成本、收益、证据等级和原始出处，只引期刊论文与官方文件。
A curated collection of Claude Opus 5.5 videos and animations: demos, original posts, prompts and workflows. English / 中文.
Lightweight image viewer for Windows with animated GIF/WEBP support
Hindsight: Agent Memory That Learns
Train transformer language models with reinforcement learning.
🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
A collection of various vulnerable (mostly physical memory exposing) drivers.
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per re…