lllm

Plurals: A System for Guiding LLMs Via Simulated Social Ensembles

Analyse environmental, social, and governance policies for potential gaps using AI - powered by LLMs, RAG techniques, and a regulatory knowledge base using OpenAI API, LangChain, Pinecone and Streamlit.

Ollama MCP Server, let's you chat with your local LLM running on your local OLLAMA server.

SVCA is a pipeline for automatically generating and uploading short-form video content to YouTube based on trending topics.

Fais - It does what you tell it to do

Production-ready WhatsApp AI dealership assistant with grounded RAG, Google Calendar booking, APScheduler reminders, FSM orchestration, Hinglish support and anti-hallucination guardrails.

GAFA takes any text or image, extracts verifiable claims, and cross-references them against the Google Fact Check API and user-provided documents to deliver evidence-based verdicts in real time.

Agente ReAct com LangGraph que responde perguntas sobre artigos científicos combinando RAG, busca web e sumarização.

AI-powered customer interview analysis tool — semantic search, insight extraction, and research synthesis built for the Great Question stack.

A simple, minimalistic, and explainable code implementation of of Nemotron 3 Nano in JAX

Production-oriented RAG pipeline for internal documents using hybrid dense + BM25 search, RRF fusion, cross-encoder reranking, confidence gating, and verified citations. Includes FastAPI APIs, Qdrant storage, evaluation benchmarks, testing, Docker deployment, and a monitoring dashboard.

Fraud detection for financial ledgers — runs entirely local (pandas/numpy), with an optional consent-gated AI layer that never sees raw transaction data by default.

Learning AI tools one at a time

RWKV/Mamba-2-style LLM which was trained 100% locally on a RTX 5050

AI-powered Personal Finance Assistant leveraging LangGraph, RAG, and real-time financial data for intelligent budgeting, expense analysis, and market insights.

AI-powered document intelligence system using RAG architecture for context-aware question answering with conversational memory and fast LLM inference via Groq.

End-to-end enterprise churn prediction, A/B experimentation and Agentic AI/RAG re-engagement platform with dbt, MLflow, FastAPI and a React dashboard.

This is mostly focused on how to make a call to LLM via API keys

An autonomous AI agent with tool-calling that decides when to fetch stock prices vs. calculate valuation ratios, built with OpenRouter.

Natural language AI agents for ROS 2 using Ollama, LangChain, Nav2, and MoveIt 2.