Core Rth. A governed AI kernel for engineers who don't trust their LLMs
Proposal-first governance + hardware E-stop for AI controlling robots/drones—legitimately novel safety architecture.
Simulates governance policies without CUDA kernels or real vLLM schedulers.
ML infrastructure researchers and LLM serving engineers
vLLM · TGI · Ray Serve
Proposal-first governance + hardware E-stop for AI controlling robots/drones—legitimately novel safety architecture.
Istio-style sidecars for AI agents solving enterprise compliance gaps.
LLM governance framework, but early-stage spec with no working code—Phase 0 skeleton promised.
Architecture spec with no AI yet — Phase 0 skeleton competing against LangChain and AutoGen.
Estimates LLM training MFU, memory, timeline across 70 models and parallelism strategies—genuinely useful before GPUs commit.
Explicit kernel control over TVM-style black boxes, but benchmarks show mixed wins vs Transformers.js.