Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

SGLang is a fast serving framework for large language models and vision language models.

Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!

A Next-Generation Training Engine Built for Ultra-Large MoE Models

RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

Deploy open-source LLMs on AWS in minutes — with OpenAI-compatible APIs and a powerful CLI/SDK toolkit.

Run ChatGPT OSS, Groke 2 Locally — GGUF Loader for 120B/20B Models | Open Source & Offline

agentsculptor is an experimental AI-powered development agent designed to analyze, refactor, and extend Python projects automatically. It uses an OpenAI-like planner–executor loop on top of a vLLM backend, combining project context analysis, structured tool calls, and iterative refinement. It has only been tested with gpt-oss-120b via vLLM.

Helper script to enable using codex-cli with LM Studio, Ollama and other LLMs

Batch processing for overnight tasks with gpt-oss 20b

MCP with GPT-OSS

This project implements a text classification system powered by Large Language Models (LLMs) running locally. The goal is to leverage the capabilities of modern LLMs to automatically categorize and label text data without relying on external APIs or manual human labeling, ensuring privacy, autonomy, and efficiency in text processing tasks.

What does gpt-oss tell us about OpenAI's training data?

finetune gpt-oss and smollm3 on your data easily and cheaply

AI CLI to scaffold complete projects and auto-fix errors. Local-first (Ollama) with OpenAI fallback

No Hopper architecture (RTX 5090, etc.) required! <16 GB VRAM, Windows.

A simple tool for semantic code search using local AI models and embeddings.

🤖 GPT-OSS Personal Assistant with RAG - Ollama를 통한 로컬 AI 비서 봇

Teaching LLMs to follow steps off a cliff

Unofficial Python client for Gradient Chat (supports gpt-oss-120b and qwen3-235b)