Stars
A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
A TTS model capable of generating ultra-realistic dialogue in one pass.
Enhanced ChatGPT Clone: Features Agents, DeepSeek, Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-4o, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message se…
Clara — Privacy-first, fully local AI workspace with Ollama LLM chat, tool calling, agent builder, Stable Diffusion, and embedded n8n-style automation. No backend. No API keys. Just your stack, you…
Model Context Protocol Servers
An MCP extension package for OpenAI Agents SDK
Fully open reproduction of DeepSeek-R1
Code implementation of synthetic continued pretraining
Instruction Tuning with GPT-4
A collection of awesome-prompt-datasets, awesome-instruction-dataset, to train ChatLLM such as chatgpt 收录各种各样的指令数据集, 用于训练 ChatLLM 模型。
🤗 smolagents: a barebones library for agents that think in code.
Minimal reproduction of DeepSeek R1-Zero
Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitching
OCR, layout analysis, reading order, table recognition in 90+ languages
Convert PDF to markdown + JSON quickly with high accuracy
Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI
Agent S: an open agentic framework that uses computers like a human
Replace 'hub' with 'ingest' in any github url to get a prompt-friendly extract of a codebase
Curator can be used to train a classifier with fewer labeled examples needed using self-supervised learning.
Python tool for converting files and office documents to Markdown.
Official repository for "DynaSaur: Large Language Agents Beyond Predefined Actions"
RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation.
Public repo to document some SPR stuff
LLM-powered multiagent persona simulation for imagination enhancement and business insights.