Ollama

This is useful for adding a local, lower-cost perspective, or for assigning a small model a targeted role: critic, exploration, or lightweight summary.

Ollama may have a slower response time than other agents, especially if the model is not already loaded. It is recommended to check that the model is loaded before starting a debate with Ollama. Or to be patient.

Install before Palabre

Install Ollama from the official documentation, then download a model.

Official documentation: https://docs.ollama.com/

CLI reference: https://docs.ollama.com/cli

Then verify that the command works:

ollama list

or:

ollama ls

If Ollama was installed after palabre init, synchronize the configuration:

palabre config --sync-agents

If needed, start Ollama:

ollama serve

Installing a model

ollama pull gemma4:e4b

Choose a model appropriate for your machine. Large models may be too heavy for smooth use.

In local use, the main limits come from your machine: memory, CPU/GPU, and response time. If you use a cloud, paid, or remote Ollama offering, quotas and limits come from that offering, not from Palabre.

Typical configuration

"ollama-local": {
  "type": "ollama",
  "baseUrl": "http://localhost:11434",
  "model": "gemma4:e4b",
  "role": "critic",
  "temperature": 0.2,
  "validateModel": true,
  "unloadOtherModels": true
}

Check if a model is loaded in Ollama

Ollama must load a model to respond quickly.

ollama ps

Automatically download a missing model

By default, Palabre does not install a model automatically. To allow it at startup:

palabre codex-ollama "Critique this plan" --pull-models

You can also enable autoPullModel in the agent configuration.

Give context to Ollama

Ollama does not read your files directly. Use:

palabre codex-ollama "Critique this module" --files src/module.ts

or:

palabre codex-ollama "Critique the architecture" --context src docs