AI Agent Skills

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

PySonar2: a semantic indexer for Python with interprocedual type inference

A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.

AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.

Run agents like Hermes and OpenClaw more securely inside NVIDIA OpenShell with managed inference

Open source alternative to AWS. Elastic compute, block storage (non replicated), firewall and load balancer, managed Postgres, K8s, AI inference, and IAM services.

14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.