ocra

Introduction

Open-CR-Agent (ocra) is an open-source, multi-agent code review system that favors precision over noise.

Open-CR-Agent (ocra) reviews code changes with a pipeline of deterministic stages around a small number of LLM agents. Code handles what must not go wrong (which files to review, how to group them, where a comment lands); models handle judgment.

Why ocra

  • Precision first. Every reviewer states what it must not flag, and findings that fail validation never reach you. A quiet review you trust beats a noisy one you skim.
  • Comments land on the right line. Models quote the code they mean; ocra resolves the quote to exact lines itself. Models never make up line numbers.
  • Plugins all the way down. VCS platforms, agent runtimes, reviewers, rule packs, tools and listeners are all plugins.
  • Any model, with failback. Configure a chain of models per tier; overloads move to the next model, short rate limits are waited out, and a model out of quota is dropped for the run.
  • Transparent cost. Every run reports input, output, reasoning and cached tokens and the cost of each attempt.
  • Measured, not guessed. Changes are evaluated on the AACR-Bench benchmark.

Status

ocra is in early development.

MilestoneScopeStatus
M1Local CLI, selection, bundling, anchoring, correctness reviewer, OpenCode runtime, plugins, evaluationDone
M2Specialized reviewers, review matrix, verification and judging, risk tiersDone
M3GitHub Action with inline comments and incremental re-reviewDone; not yet exercised on a live repository
M4Circuit breakers, remote configuration, long-term review memory, --ultra modeDone (--ultra without planning and impact analysis)

Where to next

Edit on GitHub

On this page