Free AI coding: a real agent on models that cost nothing

A coding agent that plans, edits across files and runs your tests does not have to cost $20 a month. Here is how to run More AI’s Code mode on free models, which free models are actually good at code, and where the ceiling is.

The More AI team · Updated August 21, 2026

What you get, and what it costs

Code mode points an agent at a repository: it reads the tree, plans, edits across files, runs your test suite and shows every change as a diff before anything lands. None of that is metered by us — the app is free and talks to whatever provider key you supply. Put a free key in and the whole loop costs nothing.

The agent does a lot of the work that people assume the model does. It searches the repo, keeps a plan, re-reads its own edits and re-runs the tests. That is why a mid-tier free model gets further here than the same model would in a plain chat window.

Code mode in More AI, showing a plan and a diff before changes are applied

Setting it up

Two minutes, no card. The steps below use OpenRouter because one key reaches the widest set of free models; Groq and Google AI Studio work the same way.

  1. Install More AI and open it — no account needed.
  2. In the “Start free” group of the setup step, pick OpenRouter and paste a key from openrouter.ai/keys.
  3. Switch to the Code section (⌘2) and open a repository folder.
  4. In the model picker, search “:free” and choose one of the coding-capable free models.
  5. Describe the task. Leave the access mode on “plan” for the first run so the agent proposes before it edits.

Which free models can actually write code

Not all of them can. Code needs long context, reliable tool calling and the discipline to produce a valid diff, and plenty of free models fail on the second requirement in particular — they answer well in prose and then mangle a function call.

Rather than trusting a list that ages badly, test in five minutes: give the model one small, real task in your own repository — rename a symbol across three files, or add a test for an existing function — and watch whether the tool calls land. A model that handles that will handle most day-to-day work; one that does not will not get better on a bigger task.

  • Prefer models the provider labels for code or reasoning over general chat models
  • Check the context window: below about 32k tokens, multi-file work gets frustrating
  • Open-weight families (Qwen, GLM, DeepSeek, Llama) are strongly represented in free tiers
  • If tool calls fail repeatedly, change the model rather than the prompt

Keeping a free agent honest

A cheaper model makes more mistakes, so the guardrails matter more, not less. More AI gates the agent on one axis — plan, read-only, auto, full — and every write and shell command passes a permission check you control. Start on “plan”: the agent proposes, you approve, and only then does it build.

Work on a branch or an isolated worktree, and let the agent run your tests. A free model that breaks something and then sees a red test usually fixes it; a free model editing your main branch unsupervised is a different experience entirely.

The ceiling, honestly

Free tiers cap by the day, and an agent run with many tool calls spends that allowance fast — a serious refactor can exhaust a day’s quota in one sitting. On quality, frontier models are still clearly ahead on long multi-file changes and on debugging that requires holding a lot of the system in mind at once.

What free is genuinely good for: learning the tool, small well-defined tasks, tests, refactors of a few files, and everything you would otherwise put off. When you need more, you top up your own provider key — the app does not change, and neither does your setup.

Frequently asked questions

Is the coding agent free?

The desktop app is free and runs on your own provider key, so with a free key the whole loop costs nothing. Paid cloud features are separate: they cover runs that continue while your computer is off, not the agent itself.

Can a free model really edit files across a repository?

Yes, if it handles tool calls reliably. The agent does the searching, planning and re-checking, so the model mainly has to produce correct edits. Test with one small real task before trusting it on anything large.

Will the agent change my code without asking?

Only if you let it. The access mode runs from plan (read-only, proposes first) through read-only and auto to full, and shell commands pass a rule set you control. Every change is shown as a diff.

Do I need an account?

No. The app works without signing in. An account is optional and enables the cloud — syncing sessions between devices and runs that keep going without you.

All guides