Skip to content
View antonellof's full-sized avatar
☁️
Hack the Cloud
☁️
Hack the Cloud
35 followers · 51 following

Achievements

Achievement: Public SponsorAchievement: Pair ExtraordinaireAchievement: StarstruckAchievement: YOLOAchievement: Arctic Code Vault ContributorAchievement: Pull Shark

Achievements

Achievement: Public SponsorAchievement: Pair ExtraordinaireAchievement: StarstruckAchievement: YOLOAchievement: Arctic Code Vault ContributorAchievement: Pull Shark

Block or report antonellof

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
antonellof/README.md

👋 Hello world.

I'm Antonello Fratepietro, a cloud engineer and developer passionate about building scalable Cloud and AI infrastructure. I enjoy working with modern technologies to create efficient, production-ready solutions.

Languages / Tools Used:

Programming Languages: Go Rust Python TypeScript JavaScript Bash SQL C++

Development Tools: Neovim Git Terraform Ansible Docker Kubernetes Helm Containerd Firecracker Cosign Prometheus etcd

Security & code intelligence: Semgrep Bandit Gitleaks Trivy

Frameworks & Libraries: FastAPI Actix Tonic gRPC QUIC Next.js Angular React GraphQL PostgreSQL MongoDB RocksDB Tailwind CSS shadcn/ui

Vector search & databases: Qdrant HNSW

LLM inference engines: vLLM SGLang llama.cpp TensorRT--LLM

Services Used:

Cloud Platforms: AWS Google Cloud Vercel Fly.io

APIs & Integrations: Binance OpenAI Anthropic OpenRouter

Social Media APIs: Facebook Meta LinkedIn Twitter X Pinterest Telegram

Notable Projects:

  • Ferrox - Pure-Rust GGUF inference engine with quantized CPU, Metal & CUDA kernels, MoE support, OpenAI-compatible server. Benchmarked head-to-head against llama.cpp.

  • Cognitora inference - Open-source, datacenter-scale LLM inference stack: orchestration above vLLM, SGLang, TensorRT-LLM, and llama.cpp with KV-aware routing, prefill/decode disaggregation, multi-tier KV cache, and static Rust binaries for bare metal, Kubernetes, or cloud.

  • Rondine 🐦 - Hardware-aware local LLM launcher with optimized configs for Mac, NVIDIA GPUs, and DGX Spark.

  • s0-cli - LLM-driven CLI agent that finds security vulnerabilities and AI-slop patterns (stub auth, hallucinated imports, dummy crypto, prompt-injection sinks). Hybrid of classic scanners (semgrep, bandit, gitleaks, trivy) + LLM triage, with a self-optimizing meta-harness loop.

  • VittoriaDB - Zero-configuration embedded vector database with HNSW indexing, ACID storage, and REST API. Single Go binary for local AI development.

  • DistX - High-performance vector database written in Rust. Features HNSW indexing with SIMD optimizations, Qdrant-compatible REST API, and gRPC support.

  • PeerClaw - Decentralized P2P AI agent network. One static binary. BitTorrent meets AI inference: peers share compute, agents earn & spend tokens.

Connect:

🕹️ Learned to code on a Commodore, and I've basically been hitting RUN ever since.

Pinned Loading

  1. VittoriaDB VittoriaDB Public

    Zero-configuration embedded vector database with HNSW indexing, ACID storage, and REST API. Single Go binary for local AI development.

    Go 16 1

  2. peerclaw peerclaw Public

    Decentralized P2P AI agent network. One static binary. BitTorrent meets AI inference: peers share compute, agents earn & spend tokens.

    Rust 6 1

  3. ferrox ferrox Public

    Pure-Rust GGUF inference engine with quantized CPU, Metal & CUDA kernels, MoE support, OpenAI-compatible server. Benchmarked head-to-head against llama.cpp.

    Rust 31 1

  4. vectX vectX Public

    A Qdrant-compatible vector database with explainable similarity search.

    Rust 5

  5. MARS MARS Public

    MARS (Memory for Autonomous Real-Time Systems) is a GPU-resident retrieval substrate that integrates temporal decay directly into the GPU retrieval path for real-time embodied AI — autonomous vehic…

    Cuda 1

  6. s0-cli s0-cli Public

    Security-Zero: an LLM agent CLI that runs classic SAST scanners + AI-slop detectors, then triages every finding. Self-optimizing via a Meta-Harness outer loop with a held-out benchmark.

    Python 3