robin

# Robin

> Free AI code reviews on every pull request. Robin runs as a GitHub Action in your own
> repository, calls an OpenAI-compatible LLM endpoint you configure (OpenRouter's free
> tier works), and posts severity-tiered review comments like a teammate. Bring your own
> key — no quotas, no per-seat fees, no separate service to sign up for.

## What it is

- A GitHub Action, not a hosted bot. The workflow runs in the user's repo and calls the AI URL they configure.
- Reviews on PR open; `/robin` (or `/review`) on demand; `/summary` for an overview.
- Findings are tiered High / Medium / Low / Suggestion, each with a confidence signal, posted inline on changed lines plus a summary.
- Designed to stay robust even when a weak, randomly-routed free model is used: the diff is line-numbered, the prompt is calibrated, and responses are retried with provider fallbacks.

## Setup

- From the target Git repository root, run `npx robin-review` or `curl -fsSL https://robinreview.dev/install.sh | bash`. The installer keeps one canonical `.github/workflows/robin.yml`, archives recognized historical Robin or Universal Code Reviewer workflows outside `.github/workflows`, and installs or updates the companion agent skill globally. Running either command from `~` fails because there is no target Git repository.
- Or add `.github/workflows/robin.yml` calling `antongulin/robin/.github/workflows/review.yml@main` (or pin a release tag such as `@v2`).
- Three secrets: `LLM_API_KEY`, `LLM_BASE_URL`, `LLM_MODEL`. Free OpenRouter: base `https://openrouter.ai/api/v1`, model `openrouter/free`.
- Optional `llm-temperature` input (default `0.1`, range 0–2): set it in the caller workflow's `with:` block only when the provider accepts a single fixed sampling temperature — Kimi models require `1` and reject requests otherwise. Invalid values log a warning and fall back to the default.
- Optional `reasoning-effort` setting (unset by default, provider-dependent): set it in `.github/robin.yml` as the normal per-repository location, or override it in the caller workflow's `with:` block. When unset the request contains no `reasoning` property. When set, the request uses the OpenRouter-style `reasoning: { effort, exclude: true }` object and hidden reasoning is never parsed. If a provider rejects the control or clearly rejects its value (400/422), Robin warns, retries that completion once with no reasoning override, continues that way for the run, and preserves an update-config warning in the final status comment. Auth, rate-limit, server, timeout, and unrelated validation errors do not use this fallback.

## Key files

- [README.md](README.md): human setup and usage
- [action.yml](action.yml): action inputs
- [.github/workflows/review.yml](.github/workflows/review.yml): reusable workflow consumers call
- [skills/robin/SKILL.md](skills/robin/SKILL.md): companion chat skill — drives a bounded PR review→fix→merge loop from a coding agent
- [docs/ADVANCED.md](docs/ADVANCED.md): all settings, strict mode, self-hosted runners
- [AGENTS.md](AGENTS.md): instructions for AI coding agents adding Robin to a repo

## Links

- Site: https://robinreview.dev
- Repository: https://github.com/antongulin/robin
- License: MIT
- Author: Anton Gulin — https://www.anton.qa