How does this compare to Agent Zero (frdel/agent-zero on GitHub)? Seems that provides similar functionality and uses docker for running the scripts / code generated.
Ollama provides an API endpoint that now supports the ability for an LLM to use tools/functions. Ollama is not a framework itself.
Agent Zero already can use Ollama and alternatives to run the LLMs, and this new feature should enable it to more accurately call tools that is getting built into the models that support it.
Agent Zero already can use Ollama and alternatives to run the LLMs, and this new feature should enable it to more accurately call tools that is getting built into the models that support it.