Llama-3.1 Engineer : This Coding Agent can Generate Applications, But can it beat Aider? (w/ Ollama)

Показать описание

In this video, I'll be talking about Llama-3.1 Engineer / Ollama Engineer. Llama-3.1 Engineer is an AI coding agent or Text-To-Application tool that can generate code autonomously with Agents in realtime. Although, there are some issues with it's approach that I'll be talking about in this video. This is based on the new Llama-3.1 (405B, 70B, 8B) model. I'll be generating some simple applications but you can also use it to generate Games, Applications, Web Applications, Websites, Frontend, Backend and multiple other things. You can also do Text-To-Frontend, Text-To-Application, Text-To-Game and other things with this. MicroAgent can also be used with any opensource LLM, OpenAI models or the other Claude models such as GPT-4O, Claude-3, CodeQwen, Mixtral 8x22b, Mixtral 8x7b, GPT-4, Grok-1.5 & Gemini Code Assist.

------
Resources:

------
Key Takeaways:

📈 Discover the Power of Ollama Engineer: Unleash the full potential of Ollama Engineer, an upgrade from Claude Engineer, designed to streamline your coding tasks with advanced LLM integration.

🚀 Effortless Installation & Setup: Learn how to quickly install and set up Ollama Engineer on your computer, ensuring a smooth start to your coding journey with the latest Llama-3.1 model.

💡 Enhanced Features and Commands: Explore the new features and commands that Ollama Engineer offers, including agent-based systems for efficient task management and code generation.

🛠️ Practical Coding Examples: Watch as we demonstrate practical coding examples, such as creating an HTML page and a Python program, showcasing the real-world applications of Ollama Engineer.

🔍 Tavily API Key Integration: Understand the importance of integrating the Tavily API key for web searching capabilities within Ollama Engineer, enhancing your coding efficiency.

🎮 Automode for Complex Tasks: See how the Automode feature handles complex tasks like building a snake game, with multiple iterations and agent-based tool checking for precise results.

🖥️ Comparing Ollama Engineer and Aider: Get an insightful comparison between Ollama Engineer and Aider, highlighting the pros and cons to help you choose the best tool for your coding needs.

------
Timestamps:

00:00 - Introduction
00:22 - About Ollama Engineer / Llama-3.1 Engineer
02:02 - Installation with Llama-3.1
03:56 - Usage of Ollama Engineer with Llama-3.1
06:36 - Conclusion
07:28 - Ending

Рекомендации по теме

Комментарии

You were so close to showing the Automode iterations. It's line 68. Change it to whatever you want. And change the max tokens used on line 69. Awesome video, thanks for bringing this to our attention.

spiderslim

"non-important info" - I love it. thanks for the review.

paulyflynn

but you still didnt show us how to use deepseek-v2 with aider. I am trying but it seems it is still using the older version of deepseek. I need to specify the correct deepseek version but aider does nto seem to recognise it

ganian

🔥🔥🔥 When you use aider, I’m curious what your initiation process is. For instance, for each project I’m leveraging aider for, I’ve containerized aider in a docker container and just mount to the directory aider is changing within that container. This gives me access to the files aider creates and limits the access aider has to just that container. Do you do something similar?

marioa

Why my LLama3.1 taking time to respond compare to the main one

mafmaf

Isn't Tavily just another Plattform which tracks your data in the background or so? Why isn't there an absolut independent solution out there? :(((

RealLexable

Interesting, I spent few days working a Llama 3.1 + Deepseek-coder variant of Claude-engineer. Helped me a lot to train with Aider too. On my side automode and simple chat work ok but tools calling are failing atm, it triggers the call properly but I can't reach deepseek API. I end up with a llm model not found error in that case. Any ideas?

arianetrek

Nice bro. Show me how to make a files management system, cloud-based

lovestonthebeat

hi, AICodeking

can you build a full-stack eCommerce website using Claude sonnet 3, 5 with aider

mikeyhanamichi

U need to write automode 9999 or any number do you want

yosi

Am I dreaming I thought llama is trash

Historypress-pqng

Llama-3.1 Engineer : This Coding Agent can Generate Applications, But can it beat Aider? (w/ Ollama)

Llama-3.1 Engineer : This Coding Agent can Generate Applications, But can it beat Aider? (w/ Ollama)

LLAMA-3.1 🦙: EASIET WAY To FINE-TUNE ON YOUR DATA 🙌

Build Anything with Llama 3 Agents, Here’s How

FINALLY! Open-Source 'LLaMA Code' Coding Assistant (Tutorial)

'okay, but I want Llama 3 for my specific use case' - Here's how

Build Anything with Llama 3.1 Agents, Here’s How

Llama 3.1 405B Artifacts: Code Entire Apps With One Prompt Locally - Llama Coder

Easiest Local Function Calling using Ollama and Llama 3.1 [A-Z]

Hablemos de Scala - Colombia Scala Meetup (Medellín)

Build an AI coding assistant with Llama 3 - Step 1

Aider + Llama 3.1: Develop a Full-stack App Without Writing ANY Code!

Llama vs Lava | Prompt Engineering Game using Llama3 for Pathfinding

Create Anything with LLAMA 3.1 Agents - Powered by Groq API

Llama 3.1 | Meta is leading Open Source AI

LLaMA 3 Tested!! Yes, It’s REALLY That GREAT

Fully local RAG agents with Llama 3.1

How to use Llama 3.1 ?

LlamaCoder : Generate FULL-STACK Apps for FREE with Llama-3.1 405B

Metas LLAMA 3 Just STUNNED Everyone! (Open Source GPT-4)

Llama-3.1 (405B, 70B, & 8B) + ContinueDev FREE Copilot! Fully Locally and Opensource!

Learn AI Engineer Skills: Autonomous Agentic Behavior (Llama 3 8B Ollama)

Extending Llama-3 to 1M+ Tokens - Does it Impact the Performance?

Llama 3 Fine Tuning for Dummies (with 16k, 32k,... Context)

LLaMA - Meta's new AI can run on a PC