Problem
Most agent runtimes are static: they don't learn from their own execution, lock you into one LLM provider, and offer little operational visibility.
Architecture
A pure-Rust agent runtime with a closed-loop reinforcement-learning cycle, an OpenAI-compatible API gateway, multi-provider LLM support, automatic prompt self-optimization (APO), and an operator dashboard for visibility and control.
What I built
- Closed-loop RL self-improvement cycle
- OpenAI-compatible gateway with multi-provider routing
- Automatic prompt optimization (APO)
- Operator dashboard for runtime control
Outcomes
100%
Rust, zero-GC runtime
Stack
RustReinforcement learningLLM gateways