← Open Source
fjrdomingues

autopilot

Code Autopilot, a tool that uses GPT to read a codebase, create context and solve tasks.

ApplicationsCodingJavaScript
Open on GitHub
Momentum
+0stars in 24 hours0.0%
608
Stars
61
Forks
+0
This week
5
Contributors
Created 2023-04-02 · Updated 2026-09-30 · #16174 today
Top developers

fjrdomingues/autopilot is ranked 16,174 with 608 stars.

Same-category comparison

fjrdomingues/autopilot is ranked 16,174 among these 8 peers; sturdy-dev/codereview.gpt is ranked 16,181.

Same-category comparison
NameRankMetrics
OvidijusParsiunas/myvision16,147
Language:
JavaScript
Stars:
609
Forks:
72
Description:
Computer vision based ML training data generation tool :rocket:.
botingw/rulebook-ai16,150
Language:
Python
Stars:
609
Forks:
95
Description:
Elevate vibe coding to vibe engineering: Get consistent Github Copilot custom instructions, Cursor, Roo Code, Cline, Windsurf, Claude Code, Gemini Cli, Codex CLI, kilo code, warp custom rules via a universal, managed template. Features vibe coding memory bank & best practices for large codebases.
kishan0725/AJAX-Movie-Recommendation-System-with-Sentiment-Analysis16,156
Language:
Jupyter Notebook
Stars:
609
Forks:
468
Description:
A content-based recommender system that recommends movies similar to the movie the user likes and analyses the sentiments of the reviews given by the user.
piersolenski/wtf.nvim16,164
Language:
Lua
Stars:
609
Forks:
16
Description:
Delicious diagnostic debugging in Neovim 🤤.
sturdy-dev/codereview.gpt16,181
Language:
JavaScript
Stars:
608
Forks:
75
Description:
Reviews your Pull/Merge Requests using ChatGPT.
zhang17173/Event-Extraction16,185
Language:
Python
Stars:
608
Forks:
132
aryn-ai/sycamore16,191
Language:
Python
Stars:
607
Forks:
71
Description:
🍁 Sycamore is an LLM-powered search and analytics platform for unstructured data.
yanx27/EverybodyDanceNow_reproduce_pytorch16,194
Language:
Python
Stars:
607
Forks:
172
Description:
Everybody dance now reproduced in pytorch.
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguageJavaScript
CategoryApplications
SubcategoryCoding
KeywordsCoding
Stars608
Forks61
Contributors5
Created date2023-04-02
Updated date2026-09-30
Stars in 1 day0
Stars in 7 days0
Rank16,174
Previous rank15,960
Rank change-214
7-day stars rank15,382
Previous 7-day stars rank15,388
7-day stars rank change6
Total stars rank16,622
Previous total stars rank16,596
Total stars rank change-26
CountryPortugal
README summary

Autopilot - An AI developer Autopilot is an AI tool that utilizes GPT to read a codebase, create context, and solve tasks that you request. Join our discord Join the conversation at How it works 1. You point Autopilot at a codebase with a task. AutoPilot generates and upkeeps a DB with metadata on the codebase files. AutoPilot decides which existing files it needs for the task by using the metadata DB. AutoPilot tries to implement the requested task on each

relevant file. Autopilot as a GitHub app You can use this project by installing the GitHub app available at Code Autopilot website. This app uses autopilot to automatically resolve issues that you open on GitHub and also has features for Pull Request. It provides an easy interface to use and direct integration with Github. Features 📚 - Pre-processes codebase files. 🚀 - Parallel calls to agents where possible. (Full process log with each AI interaction also produced) 🕹️ - Interactive mode - see the process with

retry, continue, abort options. Tasks expectations Referencing current code: ✅ Referencing a specific file by project relative path. ✅ Referencing a specific file by file name only, ignoring the subdirectories path. ✅ Referencing a specific function within a file without the filename. ✅ Referencing a major business concept that is exclusively used in one file. Your milage would differ by model, codebase and task. (Should introduce task scoring) Changes executed: ✅Create a new file based on an existing file. (It might empty them out

, but not delete them currently) ❌Start using new 3rd party libraries. (Needs arbitrary code execution to install the library) ❌Cascade updating related files like tests. (Coming soon) ❌Test the code it wrote and self fix. Create the file and set up the environment variables: 1. Set up an OpenAI API key and file with the key: . Set the path to your code (or use later) 4. Update Running - is the easiest way to start. Solutions will be auto applied on

your code and a git diff shown if possible. Interactive mode Use for an interactive mode, here you can review the output of each step before proceeding. 🤝 Contributing **We are running autopilot on a server connected to the repository. New issues created will trigger autopilot and create a new Pull Request with a proposal. Running with gpt-4** We welcome contributions! Please submit pull requests to the repository, and ensure your changes align with the project's goals and guidelines. Together

, we can make **Autopilot** an even more powerful and efficient tool for developers! Running tests - all runs all the tests Running tests - Unit test runs the unit tests Running tests - Benchmarks runs the end to end tests Code structure agents - interactions with language models.

Frequently asked questions

How many stars and forks are recorded?

fjrdomingues/autopilot has 608 stars and 61 forks.

What is the repository rank?

fjrdomingues/autopilot is ranked 16,174.

What language and category are recorded?

fjrdomingues/autopilot has 608 stars, uses JavaScript and belongs to Applications.

Which repository is closest in rank?

fjrdomingues/autopilot is compared with sturdy-dev/codereview.gpt, ranked 16,181 with 608 stars.

README

Autopilot - An AI developer

Autopilot is an AI tool that utilizes GPT to read a codebase, create context, and solve tasks that you request.

Join our discord

Join the conversation at https://discord.gg/r72ykfvyx7

How it works

  1. You point Autopilot at a codebase with a task.
  2. AutoPilot generates and upkeeps a DB with metadata on the codebase files. (within the codebase directory)
  3. AutoPilot decides which existing files it needs for the task by using the metadata DB.
  4. AutoPilot tries to implement the requested task on each relevant file.

Autopilot as a GitHub app

You can use this project by installing the GitHub app available at Code Autopilot website. This app uses autopilot to automatically resolve issues that you open on GitHub and also has features for Pull Request. It provides an easy interface to use and direct integration with Github.

Features

  • 📚 - Pre-processes codebase files.
  • 🤖 - Implements code changes for you.
  • 🚀 - Parallel calls to agents where possible.
  • 📝 - Shows you what was updated. (Full process log with each AI interaction also produced)
  • 🕹️ - Interactive mode - see the process with retry, continue, abort options.

Tasks expectations

  • Referencing current code:
    • ✅ Referencing a specific file by project relative path.
    • ✅ Referencing a specific file by file name only, ignoring the subdirectories path.
    • ✅ Referencing a specific function within a file without the filename.
    • ✅ Referencing a major business concept that is exclusively used in one file.
    • ✅ Referencing all project files.
    • 🤔 General logical requests. Your milage would differ by model, codebase and task. Some work. (Should introduce task scoring)
  • Changes executed:
    • ✅Create a new file based on an existing file.
    • ❌Start a new file from scratch.
    • ✅Update an existing file.
    • ✅Update multiple existing files.
    • ❌Delete existing files. (It might empty them out, but not delete them currently)
    • ❌Start using new 3rd party libraries. (Needs arbitrary code execution to install the library)
    • ❌Cascade updating related files like tests. (Coming soon)
    • ❌Test the code it wrote and self fix.

Prerequisites

nodejs v18 or above.

🛠️ Installation

  1. Clone the repository: git clone https://github.com/fjrdomingues/autopilot.git
  2. Do cd autopilot to install dependencies: npm ci
  3. Create the .env file and set up the environment variables:
    1. Copy the .env.template file to .env: cp .env.template .env
    2. Set up an OpenAI API key and file with the key: OPENAI_API_KEY=. Create openAI API key
    3. Set the path to your code CODE_DIR= (or use -d path-to-your-code later)
    4. Update IGNORE_LIST=node_modules,coverage,public,__tests__
    5. Update FILE_EXTENSIONS_TO_PROCESS=.js,.tsx,.ts,.jsx

Running

  • node ui -t "YOUR_TASK" - is the easiest way to start.
    • Solutions will be auto applied on your code and a git diff shown if possible.
    • Alternatively you may specify --auto-apply=false.
  • node ui -h - will show you all the options.

Interactive mode

Use node ui -i for an interactive mode, here you can review the output of each step before proceeding.

🤝 Contributing

We are running autopilot on a server connected to the https://github.com/fjrdomingues/autopilot repository. New issues created will trigger autopilot and create a new Pull Request with a proposal. Running with gpt-4

We welcome contributions! Please submit pull requests to the repository, and ensure your changes align with the project's goals and guidelines. Together, we can make Autopilot an even more powerful and efficient tool for developers!

Running tests - all

npm run test - runs all the tests

Running tests - Unit test

npm run unit-test - runs the unit tests

Running tests - Benchmarks

npm run e2e-test - runs the end to end tests

Code structure

  • agents - interactions with language models.
  • modules - most other internal libs.
  • ui.js - The main().
  • logs - document a task run.
Nearby in the ranking
Similar items