Local AI Setup

Sunflare can use AI for session summaries, terminal assist, and chat — all running locally, nothing sent to the cloud.

Two Options

1. Local AI Server

Run your own models on your Mac or PC using tools like LM Studio or Ollama.

LM Studio example:

1. Install LM Studio and load a model
2. Start the local server (default: http://localhost:1234)
3. In Sunflare: Settings → AI → Provider → OpenAI-Compatible
4. URL: http://localhost:1234/v1

2. Any OpenAI-Compatible API

Sunflare works with any API that speaks the OpenAI chat completions protocol:

• Ollama — http://localhost:11434/v1
• vLLM — your deployment URL
• Together AI — https://api.together.xyz/v1 + API key
• OpenAI — https://api.openai.com/v1 + API key

Access Your LLM From Anywhere

Running a local LLM at home but using Sunflare from a different network? Use Tailscale to securely access your home LLM from anywhere.