L

LLMs

Buzz is a small, self-contained companion project designed to feel calm, present, and kind.

KiM Explorer is a two-stage RAG application for transport policy research publications from the KiM Netherlands Institute for Transport Policy Analysis. Users perform semantic search to identify relevant documents, manually select publications, then interact with an LLM using full document context rather than chunks. Built with Python/NiceGUI/OpenAI API, featuring citation generation, conversation history, filtering, and web/CLI interfaces. https://explorer.kim.rijkscloud.nl/

cli llm chat client written in nim with support of ollama and openai

🔎 Type @brave in browser address bar to get results from Brave AI

🤖 nGPT: A Swiss army knife for LLMs: powerful CLI and interactive chatbot in one package. Seamlessly work with OpenAI, Ollama, Groq, Claude, Gemini, or any OpenAI-compatible API to generate code, craft git commits, rewrite text, and execute shell commands. Fast, lightweight, and designed for both casual users and developers.

https://nazdridoy.github.io/ngpt/

C++ LLM Client Using OpenRouter API

This project demonstrates how to integrate Large Language Models (LLMs) into native C++ applications using the OpenRouter API.

Key Features

OpenRouter API Integration Connect to a wide range of AI models via OpenRouter's unified API endpoint.

C++ Implementation Written in modern C++ for portability and efficiency.

Command-Line Interface Simple text-based interface for interacting with AI models.

Easy Configuration Set your API key and preferred model in a config.json file: api_key, url, model. Example:

{ "api_key": "", "url": "https://openrouter.ai/api/v1/chat/completions", "model": "deepseek/deepseek-r1-0528-qwen3-8b:free" }

Dependencies

C++11-compliant and forward-compatible

libcurl (for HTTP requests)

nlohmann/json (for JSON parsing)

Educational Value

Learn how to integrate third-party APIs in C++

Use C++ to build a minimal conversational AI interface

Serve as a starting point for more advanced native AI applications

distributed cognitive framework in Elixir/OTP.

It combines Nabla-Infinity recursive introspection (∇∞), blackboard-based shared memory, and multi-agent systems with LLM integration.

Designed for research, reasoning, training simulations, and advanced AI applications.

Tool-driven analytics agent using LLM orchestration, schema-based tools, and a semantic data dictionary.

🤖 AI chat & search summaries in Google Search, powered by the latest LLMs

🛒 AI chat & product/category summaries in Amazon shopping, powered by the latest LLMs

💬 Epic prompts to turbo-charge your LLM chatbots.

🔎 Type @you in browser address bar to get results from You.com AI

This project is focused on building and evaluating a Retrieval-Augmented Generation (RAG) system for CADE documents using RAGAS framework and CoT techniques. The system integrates advanced AI models (via AWS Bedrock), semantic search (via ChromaDB), and domain-specific datasets (CADE recomendations) to enable tasks like document analysis, question-answering, and knowledge management.

Provide FRCC DSIR the ability to securely, confidently, and efficiently answer questions informed from our team’s codebases. In places where confidence is low, it should be flagged as low to inform the person interacting with the system.

MultiNativQA is Multilingual Native question-answering (QA) dataset consisting of 64k QA pairs in seven extremely low to high resource languages, covering 18 different topics from nine different regions. Paper: https://arxiv.org/pdf/2407.09823. Project: https://nativqa.gitlab.io

Django application to build and maintain chatbots that combine the best of LLMs and rule-based engines to truly assist your users instead of manipulating them.