Goodbye GitHub Copilot, Hello Free and Local Alternatives | Open-Source & Private Coding Assistants

Are you looking for a free and local alternative to GitHub Copilot? Look no further! In this video, you'll discover open-source AI coding assistants that can help you write code faster and more efficiently. These alternatives run locally on your computer, so you don't have to worry about privacy or security.

Important Links:

#GitHubCopilotAlternatives
#OpenSourceAICodeAssistants
#FreeCodeTools
#LocalCodeTools
#CodingProductivity
#DeveloperLife
#BestAICodeAssistants
#AICodingTools
#FreeAlternatives
#LocalDevTools
#OpenSourceTools
#CodingTips
#ProductiveCoding
#DeveloperTools
#EmbraceOpenSource

[InnocentiusLacrimosa]

Would be nice to see those other options also you mentioned (open copilot etc). This landscape is changing so fast...

[CrusadeVoyager]

Nice alternatives to co-pilot, Thanks for the vid. In the future, we will be telling computers what our needs are and they code it for us on a platter ;).

[noabald]

Nice video, I’ve got forks up for llm-ls and llm-vscode to do the same thing. Hopefully it’ll be in a release soon 🤞

[denisblack]

I like the one inside Replit!
I’m against the idea, but having it setup for me I tried using it and wow it helps a lot

[richardadonnell]

🎯 Key points for quick navigation:

00:00 *💡 Introduction to GitHub Copilot and Alternatives*
- Overview of GitHub Copilot's capabilities and popularity,
- Mention of other proprietary AI coding assistants like Google's Duet AI and Amazon's CodeWhisperer,
- Introduction of the video’s focus on open-source, free, and offline alternatives to GitHub Copilot.
02:00 *🖥️ Setup and Criteria for Evaluation*
- Criteria for evaluating alternatives: ease of use, no server requirement, minimal processing power,
- Plan to use a MacBook Air M1 and Visual Studio Code for testing,
- Mention of specific open-source alternatives to be tested: Tabby and Llama Coder.
03:25 *🔧 Installing Tabby*
- Step-by-step installation process for Tabby on a MacBook Air using Homebrew,
- Overview of Tabby’s features and its integration with Visual Studio Code,
- Demonstration of setting up and running the Tabby server with the StarCoder model.
06:43 *📝 Using Tabby in Visual Studio Code*
- Detailed demonstration of Tabby’s code completion capabilities in Visual Studio Code,
- Examples of Tabby’s performance and functionality with Python code,
- Discussion of Tabby’s limitations and overall effectiveness.
16:07 *🦙 Installing and Setting Up Llama Coder*
- Instructions for installing Llama Coder and setting up the Llama model on a MacBook Air,
- Configuration of Llama Coder in Visual Studio Code,
- Downloading and running the CodeLlama model for use with Llama Coder.
22:25 *🤖 Using Llama Coder in Visual Studio Code*
- Demonstration of Llama Coder’s code completion capabilities in Visual Studio Code,
- Comparison of Llama Coder’s performance and effectiveness to Tabby,
- Discussion of potential performance issues and ways to improve them.
25:51 *📈 Conclusion and Recommendations*
- Summary of the performance and effectiveness of the open-source alternatives to GitHub Copilot,
- Encouragement to explore and utilize these free, local AI coding assistants,
- Invitation to ask questions and stay tuned for future content.

Made with HARPA AI

[TheOttacat]

I know its a rapidly changing environment, but there was no discussion of JetBrains's AI Assistant in IntelliJ which is a major miss on this topic at this time.

[zuzukouzina-original]

I think it’s a good idea to have a local dev-server running opensource code assistant AI. Than you only have to connect to it with your laptop.

[tntg]

Great video !
Thank you for sharing it.
One question : does any of these tools offer capabilities of chat within vs code ?

[adityareddy]

I have an intel based mac, I don't find anything related to it in docs, does this support for my system, I know that I can do it via docker but it slows my system down

[bennguyen]

I understand there are subscription based AI coding tools like Cody ($10/mo), CoPilot Pro ($20/mo), AWS Code Whisperer, etc..

But do the FREE tools (GPT-Pilot, gptengineer, CodiumAi, BlackBoxAI, BitoAi, CrewAI, Tabnine, Gemini) still require the GPT4 Plus subscription ($20/mo)? Or does it use the pay-per-use Assistant API pricing?

I notice some of the models at HggingFace are huge.. Do these models require training? If not, but you wanted to train it with custom data, does the size of the model grow, or does it just change and stay the same size?

Any thoughts on other tools that attempt to make it simpler to get started, like LMStudio, AnythingLLM, Oobabooga, gpt4allIo, Google Colab, llamafile, Pinokio ?

[thangnq]

need a power of GPU and Ram there are a big weakness, that why reason just pay some money to Copilot

[MarkDemarest]

"First, " "B, " and "3" are 3 spareribs conventions. 🤦🏻‍♂️ c'mon, man 😡