What we’re about
I wanted to go to meetup where folks actually build agents with LLMs, so I made one.
The idea is
- Present idea of agent, say ReAct, MemGPT, etc.
- Look over the code
- If you have a laptop and are game, try and make the agent work.
For those who are just starting out I can help with some foundation tasks like connecting to models, setting up libraries, parsing output etc.
Idea is to start without langchain, but we might lean on some libraries later on. Primarily Python but JS folks should be able to play along if it is their daily driver.
1st session will be building a tool using agent using ReAct (the idea behind ChatGPT tools), ideas for other sessions include:
- YouTube video summarization / precis
- Document summarization
- Web research agent
- Memory
- Chatting alongside other activity
- Long running agents
- Cooperative
- Reflexion
- DERA style actor critic
- RAG