AI-powered GitHub automation for issue triage, PR review, labeling, and security scanning.
aptu is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view clouatre-labs/aptu --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
Aptu is a command-line tool that uses AI to help manage GitHub repositories. It can automatically triage issues, review pull requests, suggest labels, and scan for security problems. It is designed to be fast and cheap by using small, efficient AI models.
Aptu (AI-Powered Triage Utility) is an open-source CLI and GitHub Action that automates common GitHub workflows using AI. It focuses on context engineering: instead of relying on large, expensive models, it crafts precise prompts that allow smaller models to achieve high accuracy with fewer tokens. This results in significantly lower cost and latency compared to raw API calls to large models like Claude Opus. Key capabilities include: - **Issue Triage**: Automatically summarizes issues, suggests labels, asks clarifying questions, and provides guidance to contributors. - **Issue Discovery**: Finds good-first-issues from curated repositories. - **PR Analysis**: Reviews pull requests, provides feedback, and can even create PRs from diffs. - **Security Scanning**: Built-in local security pattern detection for PR reviews; no code is sent externally. - **GitHub Action**: Auto-triage incoming issues with labels and comments. - **Multiple AI Providers**: Supports Anthropic, Cerebras, Gemini, Groq, OpenRouter (default), Z.AI, and ZenMux. - **Customizable Prompts**: Override system prompts per operation or append custom guidance. - **Observability**: Outputs context and token usage metrics for debugging. - **Multiple Output Formats**: Text, JSON, YAML, Markdown, and SARIF. Aptu is written in Rust and is available via Homebrew, Cargo, or as a GitHub Action. It is licensed under Apache-2.0 and follows best practices for security (SLSA Level 3, OpenSSF Best Practices).
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 4 days ago.
5 GitHub stars indicate community interest.
7 open issues signal maintenance load.
Apache-2.0 license detected.
Automatically triage incoming GitHub issues with AI-generated summaries and labels.
Review pull requests for code quality, correctness, and security vulnerabilities.
Discover good-first-issues for new contributors from curated repositories.
Automate dependency bump PR reviews by fetching upstream release notes.
Integrate into CI/CD pipelines as a GitHub Action for continuous triage and review.
The tool sends issue and PR content to configured AI providers (e.g., OpenRouter, Anthropic). Review provider privacy policies.
Security scanning is performed locally; no code is sent externally for that feature.
API keys for AI providers and GitHub are stored locally; ensure proper file permissions.
5
Stars
0
Forks
7
Issues
Apache-2.0
License
Suggests code changes via GitHub multi-line suggestions using reviewdog.
A CLI tool to create and hide GitHub comments using the GitHub REST API.
Local GitHub Actions runner for AI agents — test CI/CD workflows locally before pushing.
3 security/trust notes recorded.
Setup difficulty is 3/5.