Use with Ollama

Atomic Agent ships with a built-in Ollama preset. Point the agent at your local Ollama server and every model you have pulled becomes available to it. No API key is needed for a local Ollama.

What you need

• Ollama installed and running (ollama serve starts automatically with the desktop app).
• At least one model pulled.

Quick start

1. Pull a model with Ollama:

   ollama pull qwen3.6

2. Install Atomic Agent:

   curl -fsSL https://atomicagent.io/install | sh

   On Windows:

   irm https://atomicagent.io/install.ps1 | iex

3. Launch the agent:

   atomic-agent

   In the first-run setup, choose Cloud models, then pick the Ollama (local) preset. The agent lists the models you have pulled; select one and you are done.

Configure by hand

If you prefer editing config directly, add an Ollama provider to ~/.atomic-agent/config.json:

{
  "llm": {
    "activeTextProvider": "ollama",
    "providers": [
      {
        "id": "ollama",
        "kind": "openai-compatible",
        "baseUrl": "http://localhost:11434",
        "defaultChatModel": "qwen3.6"
      }
    ]
  }
}

Caution

Keep baseUrl without a trailing /v1. The agent appends the OpenAI-compatible path itself, so http://localhost:11434/v1 would produce /v1/v1/... requests and 404 errors.

Set defaultChatModel to any tag you have pulled. ollama list shows what is available on your machine.

Recommended models

Model	Good for	Approximate memory
qwen3.6	coding and agentic tool use	~24 GB
gemma4	general reasoning	~16 GB
gemma4:e4b	light option for 8 GB machines	~4 GB

Any model from ollama.com/search works as long as it fits your hardware. Models with tool-use support give the agent the best results.

Context length

Ollama picks a default context window based on available memory, and on smaller machines that can mean 4k tokens. Agent sessions carry a system prompt, tool definitions, and history, so a short window makes the model silently forget earlier turns.

If answers degrade over a session, raise the context window in Ollama:

• In the Ollama desktop app: Settings, then Context length.
• For a manually started server: set the OLLAMA_CONTEXT_LENGTH environment variable before ollama serve, for example OLLAMA_CONTEXT_LENGTH=32768.

A 32k window is a good baseline for agent work if your hardware allows it.

Troubleshooting

• 404 errors on chat requests. Check that baseUrl has no /v1 suffix.
• Empty model list. Make sure Ollama is running: ollama list should print your models.
• The local models wizard appears even though Ollama is configured. Start with atomic-agent tui --skip-llama-setup, or set ATOMIC_AGENT_TUI_SKIP_LLAMA_SETUP=1.

For the full configuration reference, see Configuration.