Skip to main content
Droid is Factory AI’s coding agent that works across your terminal and popular IDEs. It can read, modify, and execute code with multi-model support through Ollama.

​
Installation

Install Droid from Factory AI: 
curl -fsSL https://app.factory.ai/cli | sh
Learn more at factory.ai.

​
Quick Setup

ollama launch droid
Ollama automatically:
1

Selects models

Interactive multi-select picker for models
2

Configures custom models

Adds entries to ~/.factory/config.json
3

Sets token limits

Configures context windows automatically
4

Launches Droid

Starts with all configured models available

​
Configuration Only

ollama launch droid --config

​
Use Specific Model

ollama launch droid --model qwen3-coder:480b-cloud
Droid requires a large context window (at least 64k tokens). See Context Length for configuration.

​
Features

IDE Integration

Works natively in VS Code, IntelliJ, and more

Terminal Mode

Full-featured CLI interface

Multi-Model

Configure multiple models simultaneously

Cloud Support

Automatic configuration for cloud models

​
Cloud Models

qwen3-coder:480b-cloud

Recommended model for Droid (260k context)
Other excellent options:
  • glm-4.7:cloud — Reasoning and code generation (200k context)
  • deepseek-v3.1:671b-cloud — Massive reasoning model (160k context)
  • minimax-m2.5:cloud — Fast, efficient coding (200k context)
Explore more at ollama.com/search?c=cloud.

​
Local Models

  • qwen3-coder — Efficient code generation (~11GB VRAM)
  • glm-4.7 — Reasoning and coding (~25GB VRAM)
  • deepseek-coder — Specialized code model (~20GB VRAM)

​
Manual Setup

Add a configuration block to ~/.factory/config.json:
{
  "custom_models": [
    {
      "model_display_name": "qwen3-coder [Ollama]",
      "model": "qwen3-coder",
      "base_url": "http://localhost:11434/v1/",
      "api_key": "not-needed",
      "provider": "generic-chat-completion-api",
      "max_tokens": 32000
    }
  ]
}
For cloud models with larger context windows:
{
  "custom_models": [
    {
      "model_display_name": "qwen3-coder [Ollama Cloud]",
      "model": "qwen3-coder:480b-cloud",
      "base_url": "http://localhost:11434/v1/",
      "api_key": "not-needed",
      "provider": "generic-chat-completion-api",
      "max_tokens": 128000
    }
  ]
}
Ollama automatically sets appropriate token limits when you use ollama launch droid.

​
Configuration File

Droid stores configuration in ~/.factory/config.json: 
{
  "custom_models": [
    {
      "model_display_name": "glm-4.7 [Ollama]",
      "model": "glm-4.7",
      "base_url": "http://localhost:11434/v1/",
      "api_key": "not-needed",
      "provider": "generic-chat-completion-api",
      "max_tokens": 65536
    },
    {
      "model_display_name": "qwen3-coder:480b [Ollama Cloud]",
      "model": "qwen3-coder:480b-cloud",
      "base_url": "http://localhost:11434/v1/",
      "api_key": "not-needed",
      "provider": "generic-chat-completion-api",
      "max_tokens": 262144
    }
  ]
}
Ollama automatically manages this file when you use ollama launch droid.

​
Multiple Models

Droid supports multiple models simultaneously. Use ollama launch droid to configure several: 
ollama launch droid
# → Select multiple models in the picker
# → All models become available in Droid
Switch between models in the Droid UI or CLI.

​
Connecting to ollama.com

To use cloud models hosted on ollama.com:
1

Create an API key

Go to ollama.com/settings/keys
2

Export the key

export OLLAMA_API_KEY=your-key-here
3

Update config

Edit ~/.factory/config.json:
{
  "custom_models": [
    {
      "model_display_name": "qwen3-coder [Ollama Cloud]",
      "model": "qwen3-coder:480b",
      "base_url": "https://ollama.com/v1/",
      "api_key": "OLLAMA_API_KEY",
      "provider": "generic-chat-completion-api",
      "max_tokens": 128000
    }
  ]
}
4

Restart Droid

droid

​
Usage Examples

​
Terminal Mode

cd ~/projects/my-app
droid

​
IDE Integration

  1. Install the Droid plugin for your IDE
  2. Configure Ollama models in Droid settings
  3. Select a model from the model picker

​
Ask Droid to Make Changes

droid "Refactor the authentication module"

​
Switch Models

In the Droid UI, use the model selector to switch between configured models.

​
Troubleshooting

​
Model Not Available

Ensure the model is pulled: 
ollama pull qwen3-coder:480b-cloud
ollama list

​
Configuration Not Loading

Restart Droid to pick up config changes: 
droid --reload

​
Context Window Too Small

For local models, increase context: 
ollama run qwen3-coder /set parameter num_ctx 65536
See Context Length for details.

​
Connection Issues

Verify Ollama is running: 
ollama list
Check that base_url in ~/.factory/config.json matches your Ollama host.

​
Advanced Configuration

​
Custom Display Names

{
  "custom_models": [
    {
      "model_display_name": "Qwen3 Coder (Local Fast)",
      "model": "qwen3-coder",
      "base_url": "http://localhost:11434/v1/",
      "provider": "generic-chat-completion-api"
    }
  ]
}

​
Temperature and Parameters

Droid respects model-level parameters: 
{
  "custom_models": [
    {
      "model": "qwen3-coder",
      "temperature": 0.7,
      "top_p": 0.9,
      "max_tokens": 32000
    }
  ]
}

​
Environment Variables

Droid respects:
  • OLLAMA_HOST — Override Ollama server URL
  • OLLAMA_API_KEY — API key for ollama.com

​
IDE Plugins

Droid provides plugins for: After installing, configure Ollama models in the plugin settings.

​
Backup Configuration

When using ollama launch droid, Ollama creates backups in ~/.ollama/backups/ before modifying your configuration.

​
Learn More

Factory AI

Official Factory AI website

Droid Docs

Complete Droid documentation

OpenAI API

Ollama’s OpenAI-compatible API

Context Length

Configure model context windows

Build docs developers (and LLMs) love

Get started for freeTalk to us