Viewing profile — camdenclark

Separate but if you run CI at any scale you should have an agent working to improve CI constantly and alert you to any regressions / flakiness. It's something that agents can do in…

You need blocking! Fundamentally this is an entity resolution problem. An LLM can score pairwise really well but scoring all the pairs would be insanely computationally difficult. …

Absolutely the first one could be achieved using one of those tools. But Monty makes it feel so native, it even packages a type checker so you can provide stubs for the external fu…

The main property that's really important is that Monty VM state is fully serializable and resumable. So you can run the VM code until you get to a host call, then serialize and pe…

1. Control and guardrails. I want agent-authored code to be able to express itself in code but I want to own the external tools that are available to the agent. 2. Suspension and r…

Funny -- I just built a pure go wrapper myself because this one is super out of date! https://github.com/CamdenClark/monty-go It implements the new subprocess model for spawning Mo…