An open-source AI chat application that connects to any AI model and can be deployed locally or in the cloud. It requires terminal usage, a Supabase backend, and an AI model provider to operate.
Project overview
Provides a web GUI that can connect to any AI model, including options for local execution via Ollama and cloud hosting via Vercel.
Project type
Model Runtime
Use cases
Chat Assistants · Coding & Development
Deployment
Refer to project documentation
License
MIT
Best for
General users and developers seeking an open-source, self-hostable web GUI for AI chat that supports flexible model configuration.
Users who already use or can set up a Supabase backend for database and authentication requirements.
Key capabilities
Provides a chat interface that connects to any AI model.
Optional support for local AI models via Ollama integration.
Ability to deploy and host the application on cloud platforms like Vercel.
Limitations and risks
Requires a compatible node version (i.e. v18) for installation and operation.
Requires replacing values in SQL migration files manually to prevent issues with storage files not being deleted properly.
Coding knowledge is required for setup due to terminal usage and configuration steps.
Getting started
Setup difficulty is medium because it requires terminal usage, multiple configuration steps, and third-party accounts or local Docker setup. The first success path involves cloning the repo, installing npm packages, setting up Supabase, configuring the .env file, and running npm run chat.
Alternatives and comparisons
Running and managing large language models locally is complex and difficult to set up. Provides a simple way to get up and running with open models locally.
Providing a user-friendly, self-hostable, and offline-capable web interface to manage and interact with various LLM runners and AI features. An extensible, feature-rich self-hosted AI platform designed to operate entirely offline.
Enabling LLM inference with minimal setup and high performance across a wide range of hardware, locally and in the cloud. State-of-the-art LLM inference performance via a plain C/C++ implementation without any dependencies.