Inspired by Auto-GPT and BabyAGI, this is a cli tool that acts as an "agent" for LLMs and allows for longer term memory. I found the other tools not to be that great and I don't enjoy the python language nearly as much as I do the Crystal language, so here is my version!
This tool does a few things (in my opinion) better:
[x] Saves your primary agent configuration into a ~/.agentc folder instead of using the app folder [x] Saves your goals using local storage under the same ~/.agentc folder [x] Refines goals so that they can be worked. [] Creates plans for goals [] Add Pinecone client [] All of the standard capabilities are working [] All default features are tested
git clone the repo and run crystal run src/agentc.cr
Currently in development, so unless you're contributing I don't recommend trying this tool out.
To Do:
[] Everything 😉
- Fork it (https://github.com/your-github-user/agentc/fork)
- Create your feature branch (
git checkout -b my-new-feature) - Commit your changes (
git commit -am 'Add some feature') - Push to the branch (
git push origin my-new-feature) - Create a new Pull Request
- crimson-knight - creator and maintainer