Coding requires creativity. Anyone who says otherwise, is probably from the product team.😝
This means it can sometimes feel like a maze with no end in sight, especially when inspiration doesn't strike at the right moment.
Now, what if you were Din Djarin from Mandalorian and you had Grogu by your side in the time of need?
With me?
These coding copilots might not be your new best friend but tools like these can help you code faster, debug smarter, and keep your projects on track.
Well, why a list of Copilots?
Copilots improve developer productivity, and as an OpenSource tool which improves dev productivity and team's efficiency ourselves we thought why not bring more awareness to some real badass Copilots out there!
middlewarehq
/
middleware
✨ Open-source dev productivity platform for engineering teams ✨
Open-source engineering management that unlocks developer potential
Introduction
Middleware is an open-source tool designed to help engineering leaders measure and analyze the effectiveness of their teams using the DORA metrics. The DORA metrics are a set of four key values that provide insights into software delivery performance and operational efficiency.
They are:
- Deployment Frequency: The frequency of code deployments to production or an operational environment.
- Lead Time for Changes: The time it takes for a commit to make it into production.
- Mean Time to Restore: The time it takes to restore service after an incident or failure.
- Change Failure Rate: The percentage of deployments that result in failures or require remediation.
Table of Contents
Alright, moving on.
I've got 5 good ones for you so you don't have to waste your time roaming around.
1. Cursor & Copilot++
First up, we have Cursor.
This little helper is always there with the right tool at the right time.
Cursor integrates with your IDE, offering smart code completions and suggestions.
The Copilot++ by Cursor is quite a handy autocomplete feature, is quick and definitely brings useful completions to the mix.
Need to navigate your codebase? 🌏 It helps you with that too.
It’s perfect for those moments when you’re deep into the flow and need a gentle nudge in the right direction.
Cursor
This is an issues-only repo for Cursor, an editor made for programming with AI.
Creating new tickets for bugs or feature requests is much appreciated 🙂 Feel free to react to the ones you'd like us to prioritize. Our goal is to make Cursor work great for you, and your feedback is super helpful.
Getting Started
Head over to our website to download and try out the editor.
Features
It's early days, but right now Cursor can help you with a few things...
- Chat: Talk with a bot that understands your entire code base
- Edit: Ask the AI to change a block of code, see an inline diff of the edits
- Debug: Hover over linter errors or stack traces to auto-fix them
See here for more info on Cursor's features.
Roadmap
Long term, our plan is to build Cursor into the world's most productive development…
Key Features:
- Smart Code Navigation: Helps you find your way through complex codebases easily.
- Contextual Suggestions: Offers suggestions that make sense based on your current code context.
2. Tabnine
Next, meet Tabnine.
Tabnine has been around for a while and has evolved with the times, integrating GPT-4o, Tabnine+Mistral, Codestral & Claude 3 for quite powerful code suggestions.
TabNine
This is the repository for the backend of TabNine, the all-language autocompleter There are no source files here because the backend is closed source.
You can make feature requests by filing an issue. You are also welcome to make pull requests for changes to the configuration files.
languages.yml determines which file extensions are considered part of the same language. (For example, identifiers from .c files will be suggested in .h files.)
language_tokenization.json determines how languages are tokenized. For example, identifiers can contain dashes in Lisp, but not in Java.
If your feature request is specific to a particular editor's TabNine client, please file an issue in one of these repositories:
You may be interested in these TabNine clients written by third parties:
NOTE: Codota is not validating any code in those plugins and is not responsible for them by any means.
- …
Key Features:
- Security-Conscious: SOC2 compliance + strong privacy policy against training models on customer's code
- Supports Multiple Languages: Fluent in over 25 programming languages.
3. Cody by SourceGraph
Wise and powerful(like Yoda I guess), SourceGraph is all about searching and analyzing your codebase, helping you build deeper insights and understanding.
Cody is just like GitHub Copilot. That's it.
sourcegraph
/
sourcegraph
Code AI platform with Code Search & Cody
Docs •
Contributing •
Twitter •
Discord
Sourcegraph makes it easy to read, write, and fix code—even in big, complex codebases.
- Code search: Search all of your repositories across all branches and all code hosts.
- Code intelligence: Navigate code, find references, see code owners, trace history, and more.
- Fix and refactor: Roll out large-scale changes to many repositories at once and track big migrations.
Getting started
Development
Refer to the Developing Sourcegraph guide to get started.
Documentation
The doc directory has additional documentation for developing and understanding Sourcegraph:
- Architecture: high-level architecture
- Database setup: database best practices
- Go style guide
- Documentation style guide
- GraphQL API: useful tips when modifying the GraphQL API
- Contributing
License
This repository contains primarily non-OSS-licensed files. See LICENSE.
Copyright (c) 2018-present Sourcegraph Inc.
With SourceGraph, you can search across massive codebases with quite a bit of precision.
Key Features:
- Comprehensive Code Search: Searches through your entire codebase to find exactly what you need.
- Code Intelligence: Understands code semantics, making it easier to navigate and refactor your code.
4. GitHub Copilot
Okay, this one isn't technically free but worth mentioning.
It's 2024 and no AI copilot list would be complete without GitHub Copilot.
If you haven't checked out the GitHub Copilot Workspace then you definitely should try it at least once.
The ability to just formulate a plan and then verify it with natural language does feel like magic at times if you ask me.
Of course you will need to verify things, don't close your eyes and code!
GitHub Copilot might not be perfect but its really good especially because it's been trained on a huge amount of Open Source code.
It can help you not waste time on repetitive tasks by writing lines or even blocks of code.
Key Features:
- Code Suggestions: From a single line to entire functions, you've got it.
- Integration: Works seamlessly with Visual Studio Code. What? You use Vim in Arch Linux? Yes yes, you can still integrate it within Vim.😉
5. Aider.Chat
Finally, we have Aider.Chat.
Small, fast, and incredibly resourceful, Aider.Chat is all about code assistance and helps you debug like a pro.
It’s perfect for those quick fixes and debugging sessions that need speed with reliability.
paul-gauthier
/
aider
aider is AI pair programming in your terminal
Aider is AI pair programming in your terminal
Aider lets you pair program with LLMs to edit code in your local git repository Start a new project or work with an existing git repo. Aider can connect to almost any LLM. and works best with GPT-4o, Claude 3.5 Sonnet, Claude 3 Opus and DeepSeek Coder V2.
Getting started
You can get started quickly like this:
$ pip install aider-chat
# Change directory into a git repo
$ cd /to/your/git/repo
# Work with GPT-4o on your repo
$ export OPENAI_API_KEY=your-key-goes-here
$ aider
# Or, work with Anthropic's models
$ export ANTHROPIC_API_KEY=your-key-goes-here
# Claude 3 Opus
$ aider --opus
# Claude 3.5 Sonnet
$ aider --sonnet
See the installation instructions and other documentation for more details.
Features
- Run aider with the files you want to edit:
aider <file1> <file2> ... - Ask for changes
- Add new features or test cases.
- Describe a…
Key Features:
- Real-Time Assistance: Offers help as you code, making debugging and coding faster and easier. Think auto-complete on steroids. Oh yes, I did just say that.
- Good UI: Simple and intuitive.
Wrapping Up
There you have it folks, AI coding copilots to help you conquer the world.
Also, make sure to check out our Open Source repo and leave a star if you're all about developer productivity as well.
And don't forget to drop a comment below—I'd love to hear about your experiences with these AI copilots!
middlewarehq
/
middleware
✨ Open-source dev productivity platform for engineering teams ✨
Open-source engineering management that unlocks developer potential
Introduction
Middleware is an open-source tool designed to help engineering leaders measure and analyze the effectiveness of their teams using the DORA metrics. The DORA metrics are a set of four key values that provide insights into software delivery performance and operational efficiency.
They are:
- Deployment Frequency: The frequency of code deployments to production or an operational environment.
- Lead Time for Changes: The time it takes for a commit to make it into production.
- Mean Time to Restore: The time it takes to restore service after an incident or failure.
- Change Failure Rate: The percentage of deployments that result in failures or require remediation.
Table of Contents
Top comments (18)
I think these Co-Pilots will give rise to a generation of developers who wont be able to code anything from scratch, everything will be an auto complete, increasing the dependency on AI models and lower on human brains.
This is both good and bad , great for senior devs who know what they are doing, can understand the AI generated code and it will enable them to focus more on complex problems. It's bad for junior devs who will be using the AI gen code without context, making the code more error prone.
Sounds right to me. AI also has the pitfall in which it makes you feel like you're learning when you're actually not. I know that a lot of my peers already use AI on a daily basis (not just for coding, but for school and what not), and I'll be interested to see how they do when they get into a situation where they aren't able to constantly use it as a crutch.
true true, the problem solving muscle needs to be worked upon regularly - leveraging AI is a great thing but we need to stay sharp - plus ai tools aren't at a point where they produce an output that is always usable as is; if I don't know what AI is giving me, its going to bite me someday for sure
E-lafda opportunity missed since I think I agree with you on this.
Love this video by Robert Greene: youtu.be/Hkp0olCdtF4?si=f3ajgEPqsk...
We'd definitely need people to also exercise their problem solving brain while leveraging tools like this to improve efficiency.
On the code anything from scratch point, aren't we already almost there even without such tools? Boilerplates and what not - for example, most new web devs start with bootstrap - at times not having a clue what the classes are really doing on the backend to each element
Appreciate the addition here!
I will say Cursor >>> Copilot all day and these are some of the top reasons- - Cmd + L to open a smart ChatGPT
Love to see this @shivamchhuneja! ❤️ As a beginner learning to code (currently a little over 4 months in), I especially find Cursor to be so helpful, as it also has the context of the code I'm working on. Cursor has helped me to learn the right approach to problems, and its explanations also helped me to build my knowledge of concepts. ❤️
Cursor is just amazing!
totally!
This is so amazing🚀
Very well put!
thank you!
I wonder, can you install multiple ai tools on the same computer? Do they compete against each other?
Only when they use same slot for suggestion. For example, Amazon Code Whisperer and Github Copilot will conflict.
Great
thank you!
Some comments may only be visible to logged-in visitors. Sign in to view all comments.