Quickstart: Linux / macOS

The cleanest local path: macOS or Linux, Ollama on the host, codehamr in your terminal.

On Windows? See the Windows quickstart or WSL2 sandbox.

Hardware floor

Local code generation works best with a capable model, and bigger models need more memory. Here's a rough floor; smaller models run on less:

Tighter on memory? Pick a smaller model — agentic coding just gets better the more capable the model you can run. Grab a HamrPass when local isn't enough.

1. Install Ollama

macOS: download from ollama.com/download, run it. In the app, open Settings and set Context length to 64k or more (depending on your machine). The 4k default silently breaks coding agents.

Linux:

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

On Linux without the desktop app there is no slider. The context_size you set in step 4 wins.

2. Pull a model

Pick a model from ollama.com/library that fits your RAM, then use its tag in place of your-model below.

ollama pull your-model

Sizes range from a couple GB to tens of GB — bigger needs more RAM. Ctrl+C and resume works.

3. Install codehamr

curl -fsSL https://codehamr.com/install.sh | bash

Codehamr runs shell commands written by an LLM. Sandbox it in a devcontainer when it touches code you care about.

4. Point codehamr at Ollama

In your project:

active: local

models:
    local:
        llm: your-model
        url: http://localhost:11434
        key: ""
        context_size: 256000

Running codehamr in a devcontainer or WSL2 while Ollama stays on the host? The address changes and Ollama needs OLLAMA_HOST=0.0.0.0 — those guides cover it.

5. Run

codehamr

First prompt is slow while the model loads. Every prompt after is fast.

If something doesn't work

curl -s http://127.0.0.1:11434/v1/models

• JSON with your tag → recheck url: in your config.
• Connection refused → start the Ollama app, or systemctl start ollama.
• Empty model list → re-run ollama pull your-model.