Get early access, launch updates, and private demos across my LLM infra + agent tools.
Only the good stuff, I promise :)
Context deduplication layer for LLM apps
Kubernetes-style orchestration for AI agents
GPU-level LLM execution profiler
Virtual memory for LLM KV cache (VRAM → RAM → NVMe)
KV cache memory analysis tool
AI security scanner for GitHub Actions
Agent-to-Agent security framework POC
GPU cost arbitrage and multi-cloud allocation
Interactive belief-mapping tool
AI → 3D architecture generator
LLM inference parallelism research tool
Lightweight context injection helper
Have a different project in mind?