Skip to content
View ozereray's full-sized avatar
🏠
Working from home
🏠
Working from home

Block or report ozereray

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.

Content in all repositories owned by your account will be closed.
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
ozereray/README.md


⚡ About Me

Computer Science (Informatik) student at Hochschule Trier, Germany, specializing in fault-tolerant LLM infrastructure, runtime security proxies, and agentic workflows. Passionate about building production-grade backend systems and open-source reliability tooling.

  • 🛡 Core Focus: Building zero-latency runtime security layers and orchestration frameworks for autonomous AI agents.
  • 🔭 Current Venture: Founder & Core Maintainer at Aegisora (aegisora.org) — VPC-level governance and security for enterprise AI.
  • 🚀 Open Source: Author of veridian-guard, a zero-dependency Python reliability library for LLM API engineering.

🛠 Core Technical Stack

Category Technologies
Languages Python TypeScript JavaScript SQL
Backend & Infra FastAPI Docker Linux PostgreSQL Supabase
Frontend & Web Next.js TailwindCSS
AI & LLM Stack PyTorch LangChain CrewAI OpenAI Claude

🚀 Featured Architecture & Open Source

🛡 AegisoraFounder & Core Maintainer

Open-source zero-latency runtime proxy and control plane for autonomous AI agents. Intercepts agent tool/API calls inside the VPC to enforce least-privilege access and block PII leaks without bloated middleware.

veridian-guardSole Author & Maintainer

Python reliability engineering library for LLM APIs with zero runtime dependencies. Implements composable circuit-breaker decorators, dynamic fallback routing, and achieves 100% recovery rates under 0.15ms P95 overhead.

🤖 Multi-Agent Systems & Agentic Workflows

Scalable agent orchestration frameworks built with LangGraph and CrewAI. Features stateful memory layers, iterative self-correction loops, and autonomous planning over FastAPI backends with LLM streaming.

🏭 VYNO Process Guard — Industrial AI Platform

Real-time industrial process monitoring system featuring telemetry ingestion pipelines, predictive anomaly detection, and operational intelligence dashboards with adaptive alerting.


📈 GitHub Metrics


"Building robust, fault-tolerant infrastructure for the next generation of autonomous AI systems."

Pinned Loading

  1. vyno-process-guard vyno-process-guard Public

    🏭 Industrial AI monitoring platform for real-time telemetry analysis, predictive anomaly detection, and AI-powered operational intelligence.

    TypeScript

  2. multi-agent-systems-crewai multi-agent-systems-crewai Public

    A comprehensive suite of autonomous multi-agent systems built with CrewAI and LangChain, featuring sequential, parallel, and hierarchical task management for real-world business automation.

    Python

  3. veridian veridian Public

    🛡️ AI reliability middleware for fault-tolerant LLM systems, retries, fallback handling, logging, and resilient agent orchestration in production AI workflows.

    Python 1

  4. langgraph-agentic-workflows langgraph-agentic-workflows Public

    An advanced agentic workflow implementation using LangGraph and LangChain, featuring iterative research, autonomous planning, and persistent state management for high-quality content generation.

    Python 2

  5. nexar-mvp nexar-mvp Public

    🚀 Modern SaaS MVP architecture built with Next.js 15, TypeScript, and scalable component-driven frontend systems.

    TypeScript

  6. ai-coach-app ai-coach-app Public

    TypeScript