RAG
Autonomous Multi-Agent Research Framework for systematic scientific discovery
Your own sovereign, fully-local AI companion for LM Studio — bring your own chat history as memory and your research as knowledge. JARVIS-style HUD, voice, vision, autonomous live-feed awareness, and a quaternionic symbolic-cognition engine. Private by design; your AI, your machine, your data.
RAG and MCP hyperparameter tuning playbook with runnable code. Tune chunk_size, similarity_threshold, top_k, rerankers, and MCP agent guardrails. Runs offline, no API keys.
Guarded RAG: grounded answers, refuse-when-unsupported, PII redaction + eval harness. Stdlib core, bring-your-own model.
A general-purpose second-brain engine that auto-captures conversations and recalls them via semantic search + linked notes (graph)
LLM Zoomcamp - a free online course about real-life applications of LLMs. In 10 weeks you will learn how to build an AI system that answers questions about your knowledge base.
AI agent that crawls GST, SEBI, RBI, MCA & IRDAI — analyzes circulars with Claude Sonnet, tracks deadlines, and alerts teams via WhatsApp/Email/Telegram. Day 5 of 27-day AI agent build challenge.
Retrieval-Augmented Generation (RAG) chatbot for PDF documents.
Fully local, GPU-powered hybrid memory search server for LLM agents — FAISS+BM25 RRF fusion, local cross-encoder reranking, MMR, time-decay. OpenAI-compatible API, no external API.
Production-shaped telecom AI support agent with scoped tools, fine-tuned intent routing, RAG, guardrails, and adversarial evals.
Local PostgreSQL Internals Assistant with Ollama, pgvector, and MCP