TextGen (text-generation-webui)

by oobabooga

The famous "text-generation-webui", now named TextGen: a full local app for LLMs, with no telemetry.

47.7 k stars GitHub AGPL-3.0 Free when localLocalOpen sourceOpen weights

View on GitHub →

What it does

Ready-to-use portable builds (CUDA, Vulkan, ROCm, CPU)
Several backends: llama.cpp, ExLlamaV3, Transformers
OpenAI-compatible API, extensions and LoRA training

Install it

Requirements: Nothing for the portable build; Python 3.9+ for a manual install.

Download the portable build

https://github.com/oobabooga/textgen/releases

Or clone the repository

git clone https://github.com/oobabooga/textgen

Run (after pip install -r requirements/portable/requirements.txt)

python server.py --portable --api --auto-launch

The prompt for your agent

Paste it into your coding agent: it checks the requirements and installs it for you.

Claude CodeCodexCursorGemini CLIopencode

Prompt

Install TextGen (text-generation-webui) (https://github.com/oobabooga/textgen) on my machine.
1. Check the requirements: Nothing for the portable build; Python 3.9+ for a manual install. If anything is missing, tell me before installing anything.
2. Follow the official method:
- see https://github.com/oobabooga/textgen/releases
- Or clone the repository: git clone https://github.com/oobabooga/textgen
- Run (after pip install -r requirements/portable/requirements.txt): python server.py --portable --api --auto-launch
3. Check that it works, then explain how to launch it and where to start.

Always review what your agent is about to run, especially install commands.