L

LLMs

Rust implementation of the Agent2Agent (A2A) Protocol (https://a2a-protocol.org/), an open standard designed to enable seamless communication and collaboration between AI agents.

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

Projet de détection de fake news utilisant une architecture Retrieval-Augmented Generation (RAG).

Le système compare un article avec une base de données vectorielle d’articles de référence afin de prédire un verdict (TRUE / FAKE / UNCERTAIN) et générer une justification avec un LLM local.

Pipeline :

Prétraitement et découpage du texte Génération d’embeddings (Ollama) Stockage dans ChromaDB Recherche des passages similaires Vote majoritaire pour le verdict Génération d’explication avec un LLM

Technologies : Python, Ollama, ChromaDB, scikit-learn, pytest.

Projet réalisé dans le cadre de la formation Développeur en Intelligence Artificielle (Simplon).

A unified Python interface to select and use multiple Large Language Model (LLM) providers through a common API.

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

Robot Framework test harness for LLM evaluation — deterministic grading, containerized execution, multi-model comparison, safety testing, test history, and CI/CD-native.

Deterministic Reasoning Framework (DRF)

A framework for Trustworthy AI in Critical Decision Making

The Deterministic Reasoning Framework (DRF) is a command-line experimental tool designed to demonstrate a fundamental thesis in AI safety and reliability: critical decision-making tasks involving classification or ranking should not rely on pure LLM reasoning due to its stochastic and non-reproducible nature.

Perplexity Model Watcher is a Chrome extension that gives you transparency into which AI model Perplexity actually uses for your queries. Read why this is needed. Get instant visual feedback on model matches and mismatches by automatically intercepting network responses, ensuring you receive the AI experience you expect and paid for.

LLM Workflow Router is a stateless middleware engine designed to enforce explicit execution topology in AI systems that rely on large language models. It evaluates interaction metadata against strictly declared workflow rules and returns a terminal state.

🤖 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/

Simulation d’un jeu Tic Tac Toe sur une grille 10x10 avec une condition de victoire de 5 pions alignés.

Le projet fournit un moteur de jeu simple permettant de :

faire jouer deux agents (IA vs IA / LLM vs LLM) tester des stratégies connecter une interface CLI ou Web ultérieurement

Le moteur gère la logique complète :

validation des coups alternance des joueurs détection de victoire (horizontal, vertical, diagonales) détection de match nul stratégie de mouvement simple (fallback)

Projet pédagogique en algorithmie et intelligence artificielle.

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/

Convert OpenAPI and Postman to Wrekenfile and break down to mini-wrekenfiles for LLM context

Develop an ESP32-based automotive ECU simulator (ESP-IDF) implementing basic diagnostic logic (DTC management, UDS-like services, CAN simulation) with cloud LLM integration for intelligent error interpretation and repair recommendations.

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.

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