Skip to content
View NitheshK4's full-sized avatar
🥲
The compiler judged me too..........
🥲
The compiler judged me too..........

Highlights

  • Pro

Block or report NitheshK4

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
NitheshK4/README.md

Nithesh Kumar

Artificial Intelligence & Machine Learning Engineer

Building intelligent AI systems that transform data into real-world solutions through LLMs, RAG, and machine learning.

  • 🚀 Building production-ready AI applications powered by LLMs and Agentic AI
  • 🧠 Developing RAG systems, semantic search, and intelligent automation
  • 🔬 Exploring Machine Learning, Generative AI, and scalable AI architectures

Tech: Python • AI • Machine Learning • LLMs • RAG • Agentic AI • LangChain • LlamaIndex • PyTorch • TensorFlow • Git

Links

PortfolioLinkedInInstagramEmail

Pinned Loading

  1. MIRA MIRA Public

    An AI-powered platform that monitors competitor websites, detects meaningful changes using semantic analysis, scores business impact with a local LLM, and delivers actionable intelligence.

    JavaScript 2 2

  2. Pace Pace Public

    Self-hosted LLM usage, cost, and reliability observability platform for engineering teams. Track token usage, cost estimates, latency percentiles, and rate limits with 1 line of code or a zero-code…

    Python 2 2

  3. Swarmscope Swarmscope Public

    SwarmScope (Emergent Behavior Sandbox) is an advanced flight simulator and pre-deployment safety dashboard for multi-agent Large Language Model (LLM) systems. It runs Monte Carlo simulations locall…

    Python

  4. memory-firewall memory-firewall Public

    A secure gateway and policy engine for AI agent memory. Intercepts, inspects, and sanitizes read/write loops to prevent prompt injection and memory poisoning.

    Python 3 2

  5. Memora Memora Public

    A persistent, reconcilable memory graph for LLM agents — detects conflicts, validates facts, resolves contradictions, and maintains a full audit trail across sessions.

    Python 3

  6. RAG-Sentinel RAG-Sentinel Public

    Detects malicious vector index manipulation and helps secure Retrieval-Augmented Generation pipelines.

    Python 1