Back to News

Show HN: GPT-reviewer – Simple AI code reviewer for GH Actions

Hacker News - AI
Aug 5, 2025 17:54
justanotherunit
1 views
hackernewsaidiscussion

Summary

GPT-Reviewer is a new GitHub Action that leverages GPT-4o or Claude to automate code reviews, enforcing custom project rules and providing line-level feedback directly on pull requests. It supports easy configuration, custom rule files, and file filtering, streamlining the code review process with minimal setup. This tool highlights the growing integration of advanced AI models into developer workflows, enhancing code quality and efficiency through automated, customizable feedback.

GPT-Reviewer: AI-Powered Code Review GitHub Action I've built a GitHub Action that automatically reviews pull requests using GPT-4o or Claude, enforcing custom project rules through inline comments. Key Features: • Custom rule enforcement via .project-rules.md configuration • Support for both OpenAI GPT-4o and Anthropic Claude • Gitignore-style file filtering with .ignore files • Inline PR comments with specific line-level feedback • Zero-config setup beyond adding your API key, rules file and ignore file (optional) How it works: The action fetches PR diffs, parses only added lines, and sends them to your chosen AI provider along with your project rules. The AI returns structured JSON feedback that gets posted as inline comments on the specific lines that need attention. It is a one-shot prompt. Example project rules: ## Security - Never hardcode API keys or secrets - Validate all user inputs ## Code Style - Use descriptive variable names (whatever that means) - Mark typos as warnings
Read Full ArticleMore News

Related Articles

OpenAI could launch GPT-5 any minute now - what to expect

ZDNet - Artificial IntelligenceAug 5

OpenAI is reportedly on the verge of launching GPT-5, its next-generation language model, which is expected to bring significant improvements in reasoning, reliability, and multimodal capabilities. The release could set a new standard for AI performance, potentially accelerating advancements and competition in the field.

We need a new ethics for a world of AI agents

Hacker News - AIAug 5

The article argues that as AI agents become more autonomous and influential in society, existing ethical frameworks are insufficient to address the unique challenges they pose. It calls for the development of new ethical guidelines tailored to AI agents, emphasizing the need for proactive governance to ensure responsible deployment and minimize potential harms.

Show HN: Tezcat – local-first AI recall in Obsidian via a remembrance agent

Hacker News - AIAug 5

Tezcat is a proof-of-concept remembrance agent integrated with Obsidian that uses text embeddings and vector similarity search to surface relevant past notes as users write, enhancing knowledge recall without relying on traditional AI chat interfaces. Designed for a local-first experience using Ollama, it prioritizes privacy and seamless workflow integration, highlighting a trend toward more context-aware, user-centric AI tools in knowledge management.