Skip to main content

A CLI tool that automatically fixes and merges GitHub PRs using AI agents

Project description

English | 日本語

Autoland

A CLI tool that automates the fix and merge workflow after creating PRs with Vibe Coding.

Overview

AI Autoland fully automates the post-review workflow for pull requests. When you integrate AI review tools like CodeRabbit or Claude Code Review into your CI, it automatically fixes the review feedback and executes the merge.

Key Features

  • Automatic Fixes: Automatically fixes review feedback using Codex or Claude Code
  • Automatic Merge: Automatically merges after fixes are completed
  • Automatic detection and processing of open PRs
  • Waiting for GitHub checks completion
  • Automatic commit and push of fixes
  • Automatic merge decision and execution
  • Two Operation Modes:
    • Single Mode: Processes only one PR
    • Watch Mode: Continuously monitors and processes new PRs

Prerequisites

  • An AI code review tool (CodeRabbit, Claude Code Review, etc.) must be running in your CI
  • Designed for use with Vibe Coding
  • gh (GitHub CLI)
  • claude or codex command
  • Execution in a Git repository

Notes

  • This tool does not include code review functionality. It must be used in combination with external CI review tools
  • The free public version does not include code quality improvement features
  • If you need code quality improvement features, please use the commercial version that will be released in the future

Installation

pipx install autoland

Please refer to https://pipx.pypa.io/latest/installation/ for pipx installation.

Usage

Run in the target repository directory:

autoland

Repository-specific instructions

Place an AUTOLAND.md file in the target repository to share project-specific guidance (coding standards, edge cases, required checks, etc.). Its content is passed to the coding agent together with the review context when requesting fixes.

Workflow

  1. PR Detection: Selects the oldest open PR and checks out to the corresponding branch
  2. Checks Waiting: Waits for GitHub checks to complete
  3. Auto-fix: AI agent analyzes review comments and executes necessary fixes
  4. Push Changes: Commits fixes and posts a processing report as a comment
  5. Re-check: Checks for new comments and determines merge eligibility
  6. Execute Merge: Automatically merges if there are no issues
flowchart TD
  Start(["Start"]) --> Use[["Usage<br>Run in target repository: <code>autoland</code>"]]

  subgraph CLI["Process performed by CLI tool"]
    direction TB
    C0{"Are there any open PRs?"}
    C1["Select oldest open PR and<br>checkout to corresponding branch"]
    C2["Wait for GitHub checks to complete"]
    C3["Launch fixing agent and<br>pass PR context"]
    C6["Post agent-generated report<br>as PR comment"]
    C4{"Did agent add commits?"}
    C5["push"]
    C8["Merge PR"]
  end

  subgraph AG["Coding Agent"]
    direction TB
    A1["Analyze context"]
    A2{"Are there any issues?"}
    A3["Implement necessary fixes and commit"]
    A5["Create issues for out-of-scope problems<br>(if --create-issue enabled)"]
    A4_fix["Output result report (fix details)"]
    A4_ok["Output result report (no issues)"]
    A_OUT["Report"]
  end

  Use --> C0
  C0 -- Yes --> C1 --> C2
  C0 -- No --> End(["End"])

  C2 --> C3 --> A1 --> A2
  A2 -- Yes --> A3 --> A5 --> A4_fix --> A_OUT
  A2 -- No --> A5 --> A4_ok --> A_OUT

  A_OUT --> C6

  C6 --> C4
  C4 -- No (mergeable) --> C8 --> End
  C4 -- Yes (has changes to push) --> C5 --> C2

Design Principles

  • CLI does not manage authentication credentials, leverages existing tools
  • Complex decisions are delegated to AI, only mechanical decisions are implemented on the CLI side
  • Timestamped log output for long-running operations

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

autoland-0.3.0.tar.gz (16.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

autoland-0.3.0-py3-none-any.whl (20.0 kB view details)

Uploaded Python 3

File details

Details for the file autoland-0.3.0.tar.gz.

File metadata

  • Download URL: autoland-0.3.0.tar.gz
  • Upload date:
  • Size: 16.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.9

File hashes

Hashes for autoland-0.3.0.tar.gz
Algorithm Hash digest
SHA256 a349a415014a5de5cf378f7f837aa956a6d46f892cd21cc784e82abc36d85701
MD5 59832b8f1b6cc7ab96f7cd24c67eafea
BLAKE2b-256 91448f24720fd2c5f0b41b5f26430da054609325d5c1df363548caa6ec122b46

See more details on using hashes here.

File details

Details for the file autoland-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: autoland-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 20.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.9

File hashes

Hashes for autoland-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 05e42d9d1ec4e8e0169d23d39934ab9349bcbe2f266999e95524e7c23a149b59
MD5 bba44c4367eb651322bcc0afb7738503
BLAKE2b-256 0f1682a18ec40c9f5b8dcb223afca799c7dd5191a18ed3b3160c4d0e53b715eb

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page