ollama

setup

1. install ollama
2. pull a model: ollama pull llama3.2
3. configure baihu:

# ~/.baihu/config.toml
default_provider = "ollama"
default_model = "llama3.2"

no API key needed. ollama runs on http://localhost:11434 by default.

notes

• ollama is intentionally exempt from SSRF validation (it's local by design)
• supports any model available in the ollama registry
• tool use support depends on the model

custom ollama host

OLLAMA_HOST=http://192.168.1.100:11434 baihu agent