llm-engineering

Open-source implementation of AlphaEvolve

OpenAlpha_Evolve is an open-source Python framework inspired by the groundbreaking research on autonomous coding agents like DeepMind's AlphaEvolve.

Live-updating tracker of prompt engineering tools, libraries, and techniques — refreshed every 15 mi

A human–AI collaboration framework that works with LLM nature, not around it — natural language and purpose make RAG and agent orchestration unnecessary. Home of the Pang Principle.

DSSential is an advanced decision support system that leverages AI, time series forecasting, and scenario analysis to empower businesses with data-driven insights and optimization. Make smarter decisions with cutting-edge tools for forecasting, sensitivity analysis, and goal setting.

A proactive AI assistant using Qwen-Agent to learn your writing style and manage Google Calendar & Gmail.

A robust LLM Governance & ROI Evaluation platform designed to benchmark Frontier models against local open-source models. Built with an enterprise microservices architecture and cloud-ready for Kubernetes, this tool helps organizations optimize AI spend by calculating the accuracy-vs-cost tradeoff of local vs. cloud inference

Different LLM model usage projects

Twelve hands on GenAI projects in Python that take you from tutorials to shipping: LLM APIs, RAG, agents, evals, guardrails, voice, vision, and model routing. Runs on Anthropic or OpenAI, offline tests with no api key.

A high-performance local service engine for large language models, supporting various open-source models and providing OpenAI-compatible API interfaces with streaming output support.

A production-grade AI agent system implementing the ReAct (Reasoning + Acting) architecture from first principles. Built with modularity, extensibility, and cost-efficiency in mind.

Multimodal AI family coach — text, voice, and camera-aware. Learns your family. Built on Claude + Claude Vision + Web Speech API.

Technical lab for GenAI Efficiency: Bridging low-level systems (C++) with high-level AI agents to optimize inference and resource usage.

Applied LLM engineering experiments including RAG, vector search, LangChain workflows, and multi-provider AI integrations.

A simple Retrieval-Augmented Generation (RAG) app built with Streamlit. Users can upload PDFs, TXT, MD, or DOCX files and ask questions grounded entirely in the document. Supports Gemini API for contextual Q&A.

GPU-accelerated IBM Granite Code model optimization achieving 3-5x performance improvement. Complete benchmarking suite with real-time monitoring and visualization.

WhatsApp-integrated humanitarian field assistant using FastAPI, Anthropic Claude, WhatsApp Cloud API, SQLite memory, prompt guardrails, and golden-set evals.

RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

Nagizaaz Shaik — ML & AI Systems Engineer

Autonomous ReAct agent built from scratch — no LangChain. Features circuit breaker, dual database (ChromaDB + SQLite), Prometheus/Grafana monitoring, and a provider-agnostic LLM layer (Ollama/OpenAI/Anthropic). One-command Docker Compose deployment.