githubnext/agentics

A sample pack of GitHub Agentic Workflows!

What it solves

It provides a comprehensive library of reusable agentic workflows designed to automate the tedious and complex parts of software maintenance, repository management, and development lifecycles directly within GitHub.

How it works

The project offers a family of pre-configured workflows that can be integrated into a repository. These workflows use the GitHub Agentic Workflows (gh-aw) engine to perform tasks such as triaging issues, reviewing code, monitoring CI failures, and updating documentation. Some are triggered automatically (e.g., on push to main), while others are command-triggered via "/" commands in issue or pull request comments.

Who it’s for

Maintainers and developers who want to reduce the operational overhead of managing open-source or internal repositories by automating triage, quality assurance, and project planning.

Highlights

  • Maintainer Automation: Includes tools for issue triage, AI moderation of spam, and a "Repo Assist" agent for general repository assistance.
  • Fault Analysis: Tools to monitor CI workflows, investigate failures, and optimize for speed and cost.
  • Code Review: Specialized reviewers for nitpicking style or providing opinionated senior-developer feedback.
  • Documentation Maintenance: Automated updates for wikis, glossaries, and link checking.
  • Code Improvement: Agents that can analyze code for accessibility, detect duplicates, and suggest performance or energy efficiency improvements.
  • Formal Verification: Integration with Lean 4 to progressively apply formal verification to a codebase.
  • Shared Fragments: Reusable building blocks including MCP servers for arXiv and Microsoft Docs, and tools like FFmpeg.

Related

  • Project
    github/gh-aw

    GitHub Agentic Workflows (`gh-aw`) is a GitHub CLI extension that lets you write AI‑powered automation as Markdown files with YAML front‑matter. The tool compiles these *agentic* workflows into standard GitHub Actions workflows, running LLMs (Copilot, Claude, OpenAI, Gemini, Pi) in a sandboxed, read‑only mode. Writes are gated through a separate safe‑outputs job with scoped permissions. It’s designed for tasks like issue triage, PR review, CI failure analysis, docs updates, and repo reporting, integrating securely with existing CI/CD pipelines.

  • Project
    udecode/dotai

    A shared library of reusable skills and workflows for coding agents to standardize tasks like TDD, PR feedback resolution, and goal management.

  • Project
    chujianyun/skills

    A curated library of reusable Agent Skills and workflows for AI agents, covering documentation retrieval, prompt optimization, career coaching, and system operations.

  • Project
    davidondrej/skills

    A collection of reusable skill modules and instructions that AI agents can load to execute specific workflows like research, coding orchestration, and system operations.

  • Project
    sunmh207/AI-Codereview-Gitlab

    An automated AI-driven code review tool for GitLab that uses LLMs to analyze code changes and post feedback directly to merge requests.