open-code-review: an AI-powered code review CLI tool that combines deterministic engineering with an agentic workflow for high-precision defect detection
What it solves
Open Code Review is an AI-powered CLI tool designed to automate code reviews. It addresses common failures of general-purpose AI agents, such as incomplete coverage of large changesets, inaccurate line-number reporting (position drift), and inconsistent review quality caused by purely language-driven prompts.
How it works
The tool uses a hybrid architecture that combines deterministic engineering with an AI agent:
- Deterministic Engineering: Handles hard constraints like precise file selection, smart bundling of related files to manage context, and template-based rule matching to focus the model's attention.
- AI Agent: Manages dynamic decision-making and context retrieval using scenario-tuned prompts and a specialized toolset distilled from production data.
- Workflow: It reads Git diffs, sends changed files to a configurable LLM via the agent, and generates structured, line-precise review comments. It also supports a
scanmode for auditing entire files without a diff.
Who it’s for
It is built for developers and teams who want high-precision AI code reviews integrated into their local workflow or CI/CD pipelines (GitHub Actions, GitLab CI, etc.), as well as users of AI coding agents like Claude Code, Cursor, and Codex.
Highlights
- High Precision: Optimized to favor precision over noise (lower false alarms) compared to general-purpose agents.
- Resource Efficient: Consumes significantly fewer tokens and completes reviews faster than general-purpose agents.
- Tool-Use Capabilities: The agent can search the codebase, read full file contents, and inspect other changed files for context.
- Flexible Execution: Supports both OCR-managed LLMs and "Delegation Mode," where the user's own coding agent performs the review.
- Broad Integration: Compatible with multiple AI coding agents and CI/CD platforms.