Repository - AI Projects/Learning

This repo will be helpful in understanding AutoGen providing examples including prompts and agents for SAAS products, how AutoGen works, and diving into the functionality.

Current Library Versions:

<a href="https://github.com/microsoft/autogen/tree/main">

</a>
<a href="https://github.com/crewAIInc/crewAI">

</a>
<a href="https://lmstudio.ai/">

</a>

Downloads

• Ollama: https://ollama.com/
• LM Studio: https://lmstudio.ai/
• PyCharm Download: https://www.jetbrains.com/pycharm/download
• Anaconda Download: https://www.anaconda.com/download
• Visual Studio Code: https://code.visualstudio.com/
• .NET SDK: https://dotnet.microsoft.com/en-us/download

Need to KNOW:

• MemGPT has been updated recently and if we don't use memgpt configure to set the openai_key, then it won't work with OpenAI API. I opened issue here: https://github.com/tylerprogramming/ai/issues/1
• issues with function calling connected with LM Studio. GPT function calling works, but as soon as the config is swapped for localhost to LM Studio, they are ignored
• NEED to make sure that if using LM Studio, set the UserAgent to have a default auto reply to "..." or something. LM Studio complains about this because of the interaction\
• FFMPEG: must be installed to use Whisper AI
  • MACOS: https://superuser.com/questions/624561/install-ffmpeg-on-os-x
  • WINDOWS: https://phoenixnap.com/kb/ffmpeg-windows

Upcoming Ideas/Projects for Videos

• [x] crewai_flow_workout
• [ ] crewai_flow_single_llm
• [ ] crewai_infographic_creation
• [ ] crewai_docker_example
• [ ] crewai_flow_recipes
• [ ] google agent sdk
• [ ] mem0 with crewai
• [ ] full local agent setup (ollama, crewai, qdrant docker, crawl4ai, postgres docker)
• [ ] don't 'vibe' code
• [ ] Find best videos from last two weeks
• [ ] Why AI is difficult...
• [ ] 5 AI Agent Projects
• [ ] agentstack
• [ ] Lovable 2.0
• [ ] bolt.new + supabase
• [ ] replit 2.0
• [ ] ag2
• [ ] letta.ai course
• [ ] .af files