Train multi-step agents for real-world tasks using GRPO
Large Audio Language Model built for natural interactions
CineCLI is a cross-platform command-line movie browser
Stable Diffusion web UI
Tools for publishing transcripts for Claude Code sessions
Burp Suite extension for JavaScript static analysis
A lightweight text-to-speech model with zero-shot voice cloning
95% token savings. 155x faster queries. 16 languages
Refine and quantize messy AI pixel art into clean, perfect pixels
An AI-powered data science team of agents
Open source AI Agents hosted on the oTTomator Live Agent Studio
Chinese XLNet pre-trained model
Inference script for Oasis 500M
Python open source project "The Road to Self-Study Programming"
Extract audio and video content and organize it into a Markdown note
An open access book on scientific visualization using python
Document Image Parsing via Heterogeneous Anchor Prompting”
Framework for building neural networks
StreamSpeech is a seamless model for offline speech recognition
Fast forecasting with statistical and econometric models
Generate Any 3D Scene in Seconds
Automatic SSRF fuzzer and exploitation tool
Fast and Universal 3D reconstruction model for versatile tasks
A best practices guide for day 2 operations
Mini website for testing both general CS knowledge and enforce coding