alt Hacker NewsI have to check how you are using state machines but I have also been focused on small models for a while now.
nocodo is one of my product experiments, currently using 120B model but I have tested a few agents inside it with 20B models.
I create a bunch of agents, each with very specific goals. Like Project Manager, Backend Engineer, etc.
Each agent gets a very compact list of tools and access to only certain parts of the filesystem or commands.
Nice project... the per-agent tool restriction is the same core insight (smaller tool space -> better reasoning)
The main difference with Statewright is that tool access changes over time within a single agent. Planning phase gets read-only tools, edit capability unlocks after the agent proves it has adequate understanding... test tools unlock after the fix. State machines handle the phase transitions, guards and retry loops.
Your multi-agent approach decomposes by role instead of by phase/state. Both are valid. Since you're already in Rust, the engine crate (crates/engine) is a pure library with no deps. It might be interesting to see if putting a state machine around your orchestration layer improves your observed performance