micro-agent
micro-agent copied to clipboard
A tiny implementation of an autonomous agent powered by LLMs (OpenAI GPT-4)
Feature request: Consider integrating another service such as Pinecone to overcome the max token limit. It is common for developers to exceed this limit while coding
Why not let it simply use the terminal directly? Then you don't have to keep implementing and maintaining fixed actions it has to use, and it can use existing training...
Re README.md: > A file-peek state (i.e. show the function names across the code base for a high level overview) Would be nice not to have to make something for...
setup a docker file path for running to auto setup an environment for users