Provider · Ollama (local)

Linda + Ollama.

Run Linda entirely on your machine. No provider sees the traffic. Best for privacy-first apps, offline-first deployments, and demos where you don't want a real key in the browser.

Setup

# 1. install Ollama (https://ollama.com)
brew install ollama

# 2. pull a model
ollama pull llama3.3:70b

# 3. start the server
ollama serve  # default port 11434

Config

new Linda({
  transport: {
    mode: "browser",
    provider: "ollama",
    baseUrl: "http://localhost:11434",
    model: "llama3.3:70b",
  },
});

CORS

Ollama needs OLLAMA_ORIGINS set to allow browser calls:

OLLAMA_ORIGINS="http://localhost:3000" ollama serve

When to pick Ollama

Privacy: nothing leaves your machine.
Offline: no internet required after the model is pulled.
Free: no per-token cost — your hardware does the work.

See ollama.com for models + hardware requirements.

Ship an agent-driven flow this afternoon.

Install Linda, paste a config, and your form turns into an agent that fills its own inputs.

Install Linda Browse use cases