Ollama - profClaw

Ollama lets you run open-source models locally. profClaw connects to Ollama automatically - it’s always enabled and is the fallback when no cloud API keys are configured.

Supported Models

Ollama supports hundreds of models. Popular choices in profClaw:

Alias	Model	Best For
`local` / `llama`	llama3.2	General purpose
`deepseek-local`	deepseek-r1:7b	Reasoning tasks
`qwen`	qwen2.5:14b	Multilingual
`mistral-local`	mistral:7b	Fast inference

Any model available in ollama list can be used by its full name.

Most local Ollama models do not support native tool calling. profClaw automatically falls back to manual tool prompting for these models.

Setup

Install Ollama

# macOS
brew install ollama

# Linux
curl -fsSL https://ollama.com/install.sh | sh

# Windows: download from https://ollama.com

Pull a model

ollama pull llama3.2
ollama pull deepseek-r1:7b
ollama pull qwen2.5:14b

Start the Ollama server

ollama serve
# Runs at http://localhost:11434 by default

profClaw connects automatically

No API key needed. profClaw connects to Ollama at http://localhost:11434.

profclaw doctor --provider ollama

Environment Variables

string

Ollama server URL. Defaults to http://localhost:11434. Override for remote Ollama instances.

Configuration Example

.env (remote Ollama)
settings.yml
Docker Compose

OLLAMA_BASE_URL=http://192.168.1.100:11434

providers:
  ollama:
    base_url: "${OLLAMA_BASE_URL}"
    default_model: "llama3.2"

services:
  profclaw:
    image: profclaw/profclaw:latest
    environment:
      OLLAMA_BASE_URL: "http://ollama:11434"
  ollama:
    image: ollama/ollama:latest
    volumes:
      - ollama_data:/root/.ollama
volumes:
  ollama_data:

Model Aliases

Alias	Model
`local`	llama3.2
`llama`	llama3.2
`deepseek-local`	deepseek-r1:7b
`qwen`	qwen2.5:14b
`mistral-local`	mistral:7b

Usage Examples

# Use default local model
profclaw chat --model local "What is dependency injection?"

# Use a specific model by name
profclaw chat --model llama3.2 "Explain this code"

# Use any installed model
profclaw chat --model codellama:13b "Write a binary search"

import { chat } from 'profclaw';

const response = await chat("Summarize this text", {
  model: "local",
});

Notes

Ollama is always lowest priority in auto-selection. If any cloud key is set, it takes precedence.
Local models work without internet access - useful for air-gapped environments.
GPU acceleration significantly improves performance. Ollama auto-detects CUDA/Metal.
Tool calling is available via manual prompting fallback for models that don’t support it natively.

AI Providers Overview - Compare all 37 supported providers
LM Studio - Alternative local model runner with a GUI
Local LLM Guide - Run profClaw with fully local models
profclaw provider - Add and test providers from the CLI

​Supported Models

​Setup

​Environment Variables

​Configuration Example

​Model Aliases

​Usage Examples

​Notes

​Related

Supported Models

Setup

Environment Variables

Configuration Example

Model Aliases

Usage Examples

Notes

Related