Skip to content
View OshanYelena's full-sized avatar

Block or report OshanYelena

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
OshanYelena/README.md

πŸ‘‹ Hi, I'm Oshan Ranasinghe

πŸŽ“ Computer Engineering Graduate
🧠 AI Engineering β€’ Multi-Agent Systems β€’ Distributed Systems
βš™οΈ Building intelligent systems that reason, communicate, and collaborate

🀝 Connect


πŸš€ About Me

I design and build research-grade intelligent systems at the intersection of:

  • πŸ€– Agentic AI & Autonomous Systems
  • 🧠 LLM-powered Reasoning Architectures
  • πŸ”— Ontology-based Communication & Semantic Negotiation
  • 🌐 Distributed Systems & Event-Driven Architectures
  • 🚁 AI + Robotics (Vision-based autonomy)

My focus is not just building applications β€” but engineering systems of intelligence.


🧭 Current Focus

  • 🧩 STRATON-LLM
    Strategy-Oriented Negotiation Framework with LLM Mediation
    β†’ Ontology alignment + structured argumentation for multi-agent systems

  • πŸ—οΈ Lattice v0.1
    Research-grade decentralized multi-agent framework
    β†’ Async execution, agent orchestration, knowledge graphs, negotiation

  • ⚑ Deepening expertise in
    β†’ AI systems design, distributed coordination, and intelligent architectures


πŸ§ͺ Featured Projects

🧠 STRATON-LLM

Ontology-based negotiation framework for intelligent agents

Core ideas:

  • Semantic conflict detection & resolution
  • Structured argumentation protocols (multi-turn reasoning)
  • Confidence-based decision systems
  • Persistent mapping & learning layer

πŸ•ΈοΈ Lattice v0.1

Decentralized multi-agent framework (Python + asyncio)

Highlights:

  • Agent-to-agent communication (no central control)
  • Task/state orchestration with strict boundaries
  • Memory & knowledge abstraction layers
  • Observability + execution tracing

πŸ“‘ RabbitMQ Messaging Infrastructure

Event-driven communication backbone for agent systems

Includes:

  • Exchange/queue architecture (direct, topic, fanout)
  • Message schema validation & routing
  • Fault tolerance, retries, tracing
  • Async Python integration

🚁 Drone & Vision System

AI-powered autonomous drone (vision-based perception)

Focus:

  • Computer vision-driven navigation
  • Embedded AI deployment (Jetson Nano)
  • Real-time decision pipelines
  • Robotics + autonomy constraints

🧰 Tech Stack

Languages & Core Python C/C++ JavaScript

Backend & Systems FastAPI Node.js RabbitMQ gRPC REST

AI / ML LLMs CNN RL Deep Learning

Agent Systems LangChain LangGraph AutoGen

Knowledge & Semantics RDFlib Owlready2 SPARQL

Infra & Tools Docker Kubernetes AWS GCP


πŸ“ˆ What I'm Building Towards

  • AI-native distributed systems
  • Autonomous multi-agent collaboration frameworks
  • Reasoning-driven architectures on top of LLMs
  • Production-grade intelligent platforms

⭐ Always building. Always refining. Always thinking in systems.

Pinned Loading

  1. STRATON-LLM STRATON-LLM Public

    Semantic negotiation for heterogeneous agents β€” OWL-grounded, LLM-driven, courtroom-structured.

    Python

  2. ai-chatbot ai-chatbot Public

    A production - style hello world chatbot backend

    Python 1

  3. research-agent-service research-agent-service Public

    Python