textgen
Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.
TextGen is an open-source desktop application for running large language models locally with complete privacy and no telemetry. Developed by oobabooga, it supports text generation, vision capabilities, and tool-calling functions including MCP server integration. The application provides both a user interface and OpenAI/Anthropic-compatible API endpoints, enabling developers to use it as a local drop-in replacement for commercial LLM services. It works with multiple backends including llama.cpp, Transformers, and ExLlamaV3, and supports GGUF model formats out of the box.
Key Features
Use Cases
- 01Running local LLMs privately without sending data to external APIs
- 02Integrating MCP servers to extend AI agent capabilities with custom tools
- 03Replacing OpenAI or Anthropic APIs with a local alternative for development and testing
- 04Processing documents and images with multimodal models entirely offline
- 05Fine-tuning LoRA adapters on custom chat datasets for specialized applications
- 06Deploying self-hosted LLM inference with web search and math tool-calling
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
textgen — FAQ
What is TextGen MCP server?+
TextGen is a desktop application for running local LLMs that includes MCP server support as part of its tool-calling system. It allows AI models to call custom functions and integrate with external MCP servers during chat conversations.
How do I install TextGen?+
Download the portable build from the GitHub releases page, unzip it, and double-click the textgen executable. For full installation with additional features, clone the repository and run the platform-specific startup script (start_windows.bat, start_linux.sh, or start_macos.sh).
Which AI clients work with TextGen?+
TextGen provides OpenAI and Anthropic-compatible API endpoints, so any client supporting those APIs can connect to it. It also includes its own Gradio-based web interface and optional Electron desktop window.
Do I need API keys to use TextGen?+
No API keys are required for basic operation since TextGen runs models locally. You can optionally set an API key for authentication when exposing the API server.
Is TextGen free to use?+
Yes, TextGen is completely free and open-source with no telemetry or usage restrictions. You only need to download compatible GGUF model files separately from Hugging Face.
What are the prerequisites for running TextGen?+
For portable builds, no prerequisites are needed—all dependencies are included. For manual installation, you need Python 3.9+ or Conda, and optionally a CUDA-compatible NVIDIA GPU for accelerated inference.
How do I install textgen?+
Open the source repository on GitHub and follow its README. textgen is a mcp server — MCP Agents Market links you directly to the official repo.
Is textgen free?+
textgen is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.