career-ops

Set up a free AI engine

Use career-ops for $0: OpenCode with a free provider, a local model via Ollama, or any OpenAI-compatible endpoint, plus what to do when tokens run out.

No, you do not need a Claude subscription — or any paid plan — to run career-ops. career-ops is free and open source (MIT), and its AI engine can be free too: OpenCode with a free provider, a fully local model via Ollama, any OpenAI-compatible endpoint, or the built-in OpenRouter runner. If you have run out of tokens mid-search, switching to a free engine takes minutes and leaves your CV, pipeline and reports untouched.

career-ops has no paid plans, no tiers, no trials — it is 100% free and MIT-licensed. Any site describing career-ops pricing is describing a different product. The one thing career-ops needs to think is an AI engine — an AI coding assistant that reads its prompts and does the work. That engine can be free too.

With career-ops you bring your own engine and your own key. Nothing runs on career-ops servers — everything happens on your machine. This page shows the free paths, from the easiest to the most hands-on. Pick one and you're ready for the Quick Start.

What am I actually setting up?

Think of career-ops as the recipe and the AI engine as the cook. The recipe is free forever. This page is about getting a cook for free — whether that's a hosted model with a free tier or a model running entirely on your own computer.

Which path is right for me?

If you want…UseFree?Needs a good computer?
The easiest free startOpenCode + a free providerYesNo
Everything 100% offline & privateOllama (local model)YesYes — 16GB+ VRAM
To reuse a CLI you already haveIts own free tierIf it has oneNo
The one-command shortcutnpm run orYesNo

Most people should start with OpenCode and a free provider; the other paths are here when you want them.

Before you send your CV to a free tier

Some free tiers may use what you send to improve their products, and people may review it. Your CV is personal information, so read the provider's terms before you pass it along. With a local model through Ollama, nothing leaves your computer.

OpenCode is a free, open-source AI coding assistant. From career-ops' creator, Santiago Fernández de Valderrama Aparicio: "opencode is top." OpenCode connects to plenty of providers that offer a free tier, so you can run career-ops without spending anything.

Follow the one-line install on opencode.ai. It runs in your terminal, like the other AI CLIs.

Sign up for any provider with a free tier and copy your API key. Popular free options the community uses: OpenRouter (models tagged :free), Google AI Studio (Gemini free tier), and OpenAI-compatible endpoints like Nvidia's free tier. The budget guide keeps the up-to-date list of models that hold up well.

Open OpenCode inside the career-ops folder:

Terminal
opencode

Inside OpenCode, run /connect, choose your provider (for example OpenRouter) and paste your key. Then run /models and pick a free model — on OpenRouter, one tagged :free. OpenCode ignores OPENAI_API_BASE and OPENAI_BASE_URL; /connect and /models are what set it up.

That's it — OpenCode is now your engine. Head to the Quick Start.

Path 2 — A CLI you already have

If you already use a supported CLI — Claude Code, OpenCode, Codex, GitHub Copilot CLI, and more — career-ops works with it, and several of those CLIs ship a free tier. Open your CLI inside the career-ops folder; this path needs no extra setup.

Path 3 — 100% local with Ollama (fully offline)

For zero cloud, zero cost, and total privacy, run the career-ops AI engine on your own machine with Ollama. Nothing leaves your computer.

The trade-off of running career-ops locally is hardware. career-ops asks the model to score jobs across many dimensions and tailor your CV — small models struggle with that.

Pick a model that's big enough

For career-ops on a local model, skip the tiny 7–8B models — they fail the scoring format and produce generic CVs. Use a 32B model or larger (e.g. Qwen 2.5 Coder 32B), which needs a GPU with 16–24GB of VRAM (an RTX 3090/4090, or an Apple Silicon Mac with 32GB+ unified memory). Without such a machine, OpenCode with a free provider (Path 1) is the better free route.

Terminal
# Install Ollama from ollama.com, then pull a capable model:
ollama pull qwen2.5-coder:32b

After pulling the model, point your AI CLI (OpenCode works well here) at the local Ollama endpoint, or use the built-in local evaluator described in the budget guide.

Path 4 — The one-command shortcut: npm run or

career-ops ships a built-in runner that routes to OpenRouter's free models with automatic fallback — no CLI configuration to fiddle with. Once you've cloned career-ops and set an OpenRouter key, one command runs the pipeline:

Terminal
export OPENROUTER_API_KEY="your_free_key_here"
npm run or            # runs the full pipeline on free models

The npm run or runner also has focused variants — npm run or:scan, or:eval, or:apply — for running a single step.


For developers — tune models & cost

The core career-ops repo's Running on a Budget guide goes deep on maintained model recommendations, per-provider examples, standalone evaluators (node openai-eval.mjs, node ollama-eval.mjs), and token-saving flags. career-ops is fully model-agnostic — point it at any OpenAI-compatible endpoint with zero code changes.

You're ready

Once your engine is set up, continue to the Quick Start — you'll clone career-ops, add your CV, and run your first free scan.

Still choosing a tool? Read how to choose an AI job search agent.

On this page