Autonomous AI agent framework that runs unattended on GitHub Actions with self-healing skills.
aeon is worth checking the docs before setup with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view aeonfun/aeon --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.
Repository setup guidance
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 24 days ago.
667 GitHub stars indicate community interest.
1 open issues signal maintenance load.
MIT license detected.
4 security/trust notes recorded.
Setup difficulty is 3/5.
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.
AI-powered GitHub automation for issue triage, PR review, labeling, and security scanning.
Suggests code changes via GitHub multi-line suggestions using reviewdog.
Aeon is a tool that lets AI agents work on their own without needing someone to approve every step. It runs on GitHub Actions, so it can keep working even when you're not around. It can fix its own problems and works with different AI models like Claude and Codex.
Aeon is a framework designed to create fully autonomous AI agents that operate without human intervention. It leverages GitHub Actions to run continuously, allowing agents to execute tasks, manage workflows, and make decisions independently. Key features include self-healing skills that enable agents to recover from errors, and integration with multiple AI models such as Claude Code, Grok, and Codex. The framework emphasizes a 'configure once, forget forever' philosophy, reducing the need for constant oversight. It is built with TypeScript and is open-source under the MIT license. Aeon is suitable for automating complex DevOps tasks, managing repositories, and handling repetitive workflows, making it a powerful tool for developers seeking to streamline their operations.
667
Stars
239
Forks
1
Issues
MIT
License
Autonomous AI agent framework that runs unattended on GitHub Actions with self-healing skills.
DevOps engineers looking to automate infrastructure tasks., Developers who want to reduce manual oversight in their workflows., Tech leads aiming to implement autonomous agents in their teams.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Autonomous agents may perform unintended actions if not properly sandboxed. Running agents on GitHub Actions may incur costs or resource usage.
Similar or complementary options to evaluate include github-comment, Agent-CI, aptu.
Aug 20, 2026