Features
Custom microarchitecture for NP-complete problems
7000x speedup on subset sum decision problem vs software
Removes memory access bottlenecks in optimization
Harmonized hardware-algorithm instruction sequences
Targets practical applications of combinatorial optimization
High-throughput processing for complex decisions
FPGA-accelerated prototype available
Organic architecture design philosophy
Distributed tracing for LLM agents
Capture prompts, retrievals, tool calls, outputs
Human annotations on traces
Create datasets from traces
Run experiments to compare changes
OpenTelemetry-native instrumentation
Self-host locally, Docker, or Kubernetes
Cloud instances with free tier
Vendor agnostic: any model or framework
3M+ monthly downloads, 9k+ GitHub stars
