Skip to content
View oneKn8's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report oneKn8

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
oneKn8/README.md

Hi, I'm Santo

Dallas, TX | CS @ UT Dallas | Systems, AI/ML, and infrastructure

Python TypeScript C++ Go Rust Java Linux Docker Codex Claude Code

I build production systems from scratch -- vector databases, task queues, research agents, observability platforms. Most of my work sits at the intersection of systems programming and applied ML.

Projects

  • Soniq - AI voice agents for business phone handling. Full-stack voice pipeline (Deepgram STT, Cartesia TTS, LLM orchestration) with sub-500ms latency. Multi-tenant architecture, CRM, calendar sync (Google/Outlook/Calendly), 27 industry presets. TypeScript Next.js Python LiveKit Supabase

  • VectorVault - HNSW approximate nearest neighbor engine from scratch in C++20. AVX2 SIMD-accelerated distance computation, memory-mapped persistence, sub-millisecond queries at 100k vectors. C++ CMake Docker

  • OpenLock - Open-source lockdown exam browser for Linux. Implements the SEB protocol (BEK + Config Key + RNCryptor v3), kiosk shell, process guard with cgroups, VM/debugger detection. C++ Qt Chromium

  • QUASAR - Quantum circuit discovery agent. Physics-augmented LLM proposes candidates, surrogate model filters 10k+ in milliseconds, top 10% go through full VQE optimization. Python PyTorch Qiskit

  • Socratic - Private, multi-model alternative to NotebookLM. 16+ providers, podcast generation, vector search, multi-modal content ingestion. Runs entirely local. TypeScript Next.js Python LangChain

  • Syzygy - Document engineering IDE. Rust + Tauri 2.0 + Typst backend, visual pipelines, AI-assisted document creation. Rust Tauri Typst

  • SearchLight - Hybrid search API combining BM25 keyword matching and HNSW vector similarity via Lucene 9. Hexagonal architecture, Spring Boot 3.3, Prometheus + OpenTelemetry. Java Spring Lucene Prometheus

  • RivetQ - Durable task queue with write-ahead log, Raft consensus for HA, priority queues, dead-letter queues, rate limiting. REST + gRPC, Prometheus metrics, Next.js admin UI. Go gRPC Prometheus Next.js

  • Research Agent - Autonomous research pipeline using LangGraph with locally-hosted DeepSeek-R1-14B via vLLM. Adaptive planning, web + ArXiv search, gap analysis, LaTeX output with citations. Python FastAPI vLLM LangGraph

  • Pulse - HPC cluster observability platform. GPU/node telemetry, SLURM-style scheduling, Prometheus + Alertmanager + Grafana, VictoriaMetrics, LLM-based ops assistant via Ollama + RAG. Go Prometheus Grafana React

  • SysVitals - Real-time system health monitoring dashboard. CPU, memory, network, storage, services, security -- all over WebSocket, zero polling. Runs 100% locally. Python FastAPI React WebSocket

  • undertone - Voice typing daemon for Linux. Hold a key, speak, release -- text appears at your cursor in <1s. Groq Whisper with local faster-whisper fallback. Python Whisper Linux

  • mcp-memory - MCP server for persistent agent memory with semantic search. ChromaDB embeddings, per-project scoping, importance scoring. Fully local. Python ChromaDB MCP

  • Pulp - Document intelligence CLI. Drop a PDF, ask questions, get answers. Multi-provider LLM backend (OpenAI, Anthropic, Ollama). Terminal-native TUI. Go CLI

  • Ghost Browser - Privacy-focused desktop browser. Electron + Rust core via napi-rs, React/Vite frontend, SQLite storage. Electron Rust React

  • scaffold - Project bootstrapper CLI for Go, Rust, Python, and TypeScript. Go CLI

  • gitpulse - GitHub stats CLI dashboard -- track contributions, streaks, and achievement progress from the terminal. Go CLI

  • llm-cost - Multi-provider LLM API cost tracker across OpenAI, Anthropic, Groq, Google, DeepSeek. Go CLI

GitHub Activity

GitHub Stats

GitHub Streak

Contribution Graph


X LinkedIn Email Instagram Discord GitHub

Pinned Loading

  1. RivetQ RivetQ Public

    Durable task queue with write-ahead log, Raft consensus for HA, priority queues, dead-letter queues, rate limiting. REST + gRPC APIs, Prometheus metrics, Next.js admin UI.

    Go 1

  2. VectorVault VectorVault Public

    HNSW approximate nearest neighbor engine from scratch in C++20. AVX2 SIMD-accelerated distance computation, memory-mapped persistence, sub-millisecond queries at 100k vectors.

    C++ 1

  3. openlock_browser openlock_browser Public

    Open-source lockdown exam browser for Linux. SEB protocol implementation (BEK + Config Key + RNCryptor v3), kiosk shell, process guard with cgroups, VM/debugger detection.

    C++ 5 1

  4. searchLight searchLight Public

    Hybrid search API combining BM25 keyword matching and HNSW vector similarity via Lucene 9. Hexagonal architecture, Spring Boot 3.3, Prometheus + OpenTelemetry.

    Java 1

  5. socratic socratic Public

    A private, multi-model, full-featured alternative to Notebook LM

    TypeScript 1

  6. soniq soniq Public

    AI voice agents for business phone handling. Sub-500ms latency, multi-tenant, 27 industry presets.

    TypeScript 1