Nikita-Filonov/ai-review

What it solves

AI Review is designed to reduce noise in pull requests and speed up the code review process. It automates the detection of issues, enforces coding consistency, and provides high-level summaries of changes, reducing the manual effort required by human reviewers.

How it works

The tool integrates directly into CI/CD pipelines (such as GitHub Actions or GitLab CI/CD) and uses Large Language Models (LLMs) to analyze code changes. It can operate in several modes:

• Inline Mode: Adds line-by-line comments directly in the diff.
• Context Mode: Analyzes multiple files to detect cross-file inconsistencies.
• Summary Mode: Provides a high-level overview of the strengths and major issues of a PR.
• Reply Mode: Participates in existing review threads to provide follow-up replies.
• Agent Mode: Uses a ReAct-style loop to autonomously explore the repository using shell commands (like ls, cat, rg, git) to gather deeper context before producing a final review.

Who it’s for

Software development teams who want to automate parts of their code review workflow across various Version Control Systems (VCS) like GitHub, GitLab, Bitbucket, Azure DevOps, and Gitea.

Highlights

• Broad LLM Support: Compatible with OpenAI, Claude, Gemini, Ollama, Bedrock, OpenRouter, and Azure OpenAI.
• VCS Integration: Works out-of-the-box with major platforms including GitHub, GitLab, and Bitbucket.
• Agentic Capabilities: Ability to explore the codebase autonomously for more context-aware feedback.
• Privacy-focused: Runs client-side and does not proxy or store source code; supports local LLMs via Ollama for offline reviews.