Ferry: Jira-Driven Autonomous Development on GitHub Actions
This repository profile is provided by osrepos.com, an open source repository discovery platform.

Summary
Ferry is an innovative GitHub Actions-native agent pipeline designed to automate your development workflow. It seamlessly integrates with Jira, transforming column moves into reviewed draft pull requests without requiring any server or daemon. This tool empowers teams to achieve a fully autonomous development loop, from ticket refinement to merged PRs.
Repository Information
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
Ferry is a powerful GitHub Actions-native agent pipeline that streamlines the development process by connecting your Jira board directly to an autonomous dev loop. It eliminates the need for manual intervention by converting Jira column transitions into reviewed draft pull requests, all without the overhead of a dedicated server or daemon. Built with TypeScript, Ferry offers a robust solution for automating your software delivery pipeline.
Why Use It and Benefits
Ferry provides significant advantages for teams looking to enhance their productivity and reduce manual effort. Its core benefit lies in creating a fully autonomous development workflow, where agents like Refiner, Developer, Reviewer, Iterator, and Merger run as GitHub Actions workflows. These are triggered automatically by Jira ticket column moves, ensuring a continuous and efficient flow from task assignment to code deployment. This automation minimizes human error, accelerates delivery times, and allows developers to focus on more complex tasks, while Ferry handles the repetitive aspects of the development cycle. It also supports experimental GitLab CI, expanding its utility.
Installation
Getting started with Ferry requires Node.js version 20 or higher and a Jira Cloud project. The installation process is straightforward, primarily involving a single command to initialize the setup.
npx -p @big-emotion/ferry ferry-init
After initialization, simply move a Jira ticket into your "Refinement" column, and Ferry will take over, orchestrating the subsequent development steps. For detailed instructions, including GitHub Actions and experimental GitLab CI paths, refer to the official installation guide.
Examples
Ferry's workflow is designed to be intuitive and highly automated. It follows a clear path:
Jira board ??> repository_dispatch ??> GitHub Actions ??> merged PR
(you) (automatic) (autonomous) (automatic)
This means that once a Jira ticket is moved, Ferry's agents automatically trigger a series of actions, leading to the creation and eventual merging of a pull request. Ferry also includes several CLI commands for managing your setup, such as ferry-init, ferry-doctor, ferry-update, and ferry-uninstall, providing comprehensive control over the automation pipeline.
Links
Related repositories
Similar repositories that may be relevant next.
awesome-grok-bot: A Curated List of Grok Bot Resources and Tools
August 31, 2026
The `awesome-grok-bot` repository is a comprehensive, bilingual collection of resources for Grok Bot, the always-on AI teammates with dedicated cloud computers. It provides curated links to official documentation, tutorials, real-world use cases, and community discussions. This list is an invaluable guide for anyone looking to explore or implement Grok Bot solutions.

gh-aw: Automating GitHub Workflows with AI Agents
August 29, 2026
GitHub Agentic Workflows (gh-aw) is a powerful GitHub CLI extension that enables AI-powered repository automation. It allows developers to define intelligent, agentic workflows using Markdown with YAML frontmatter, which are then compiled into standard GitHub Actions workflows. This tool complements traditional CI/CD by handling tasks requiring reasoning or interpretation, such as issue triage and pull request reviews, leveraging AI engines like GitHub Copilot and Claude Code.

Autoresearch: Autonomous Iteration for LLM-Powered Code Improvement
August 24, 2026
Autoresearch is a powerful GitHub repository that transforms large language models like Claude Code, OpenCode, and OpenAI Codex into relentless improvement engines. Inspired by Karpathy's autoresearch, it enables autonomous, goal-directed iteration, following a "Modify, Verify, Keep/Discard, Repeat" loop to achieve compounding gains across various domains. This project offers a structured approach to automate development, security, and operational tasks with AI.

claude-code-codex-bridge: Sync Your Claude Code Setup with Codex
August 23, 2026
The `claude-code-codex-bridge` is a Python tool that automatically synchronizes your Claude Code setup, including plugins, skills, agents, and commands, with Codex. This one-way bridge ensures that any changes made in Claude Code are reflected in Codex, keeping both environments equally effective. It streamlines the management of AI coding tools by allowing you to configure once and deploy across both platforms.
Source repository
Open the original repository on GitHub.