- All languages
- Awk
- Batchfile
- BitBake
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Cuda
- Cython
- Dart
- Dockerfile
- Elixir
- Emacs Lisp
- Erlang
- Fluent
- Fortran
- Go
- HCL
- HTML
- Haskell
- Java
- JavaScript
- Jinja
- Julia
- Jupyter Notebook
- Kotlin
- Lua
- MATLAB
- Makefile
- Markdown
- Mermaid
- Nim
- OCaml
- Objective-C
- OpenEdge ABL
- PHP
- Pascal
- Perl
- PowerShell
- Puppet
- Python
- QML
- R
- Rich Text Format
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Solidity
- Starlark
- Swift
- TSQL
- Tcl
- TeX
- Terra
- TypeScript
- Vue
- Wikitext
- reStructuredText
Starred repositories
Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
PineScript v6 Language Support plugin for IntelliJ IDEA
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
Fully automatic censorship removal for language models
The absolute trainer to light up AI agents.
GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image Generation.
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line …
π RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection — all without a single pixel of video.
VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
Unsloth Studio is a web UI for training and running open models like Qwen, DeepSeek, gpt-oss and Gemma locally.
Download an entire website from the Wayback Machine.
Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).
Simultaneous speech-to-text models
ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Robust Speech Recognition via Large-Scale Weak Supervision
The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how t…
🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT!🌏 Train a 64M-parameter GPT from scratch in just 2h!
Self-hosted video downloader for YouTube and other sites (web UI for youtube-dl / yt-dlp)
[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent 🤖
A practical Douyin downloader for both single-item and profile batch downloads, with progress display, retries, SQLite deduplication, and browser fallback support. 抖音批量下载工具,去水印,支持视频、图集、合集、音乐(原声)。免费…
The official code repository for LeVo: High-Quality Song Generation with Multi-Preference Alignment
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.
🐋 Ansible playbook which helps you host various FOSS services as Docker containers on your own server
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.