An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.

Desktop AI Assistant powered by o1, o3-mini, GPT-4, GPT-4 Vision, Gemini, Claude, Llama 3, DeepSeek, Bielik, DALL-E, chat, vision, voice control, image generation and analysis, agents, command execution, file upload/download, speech synthesis and recognition, access to Web, memory, presets, assistants, plugins, and more. Linux, Windows, Mac

First class Sublime Text AI assistant with o1, o3-mini and ollama support!

Hallucinations (Confabulations) Document-Based Benchmark for RAG

Providing Duckduckgo AI Chat API, which can use o3-mini for free.

Use Duckduckgo AI Chat to provide an OpenAI-compatible API that can be used for free with o3-mini.

LLM-powered assistant for creating, editing, and interpreting business process diagrams

LLM public goods game

State Sandbox is an experimental game for socioeconomic simulation. It uses Large Language Models (o3-mini) to simulate the world and complex policy impacts.

A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private conversations, form alliances, and vote to eliminate each other

A clean, lightweight, and modern Python client for PerplexityAI's API.

Solving Inverse Kinematics using Large Language Models

Open Source Deep Research

📖Curated list about reasoning abilitiy of MLLM, including OpenAI o1, OpenAI o3-mini, and Slow-Thinking.

This is an educational OpenAI project for my colleagues, which demonstrates concepts of using the streaming output with regular OpenAI and Azure OpenAI clients. Highlights:1.Streaming output 2.Difference in streaming performance of gpt-4o&o1 models 3.Usage of keyless Entra ID auth in Azure OpenAI 4.The "Stop" button. node 5.Code- and Text- prompts

Este repositório contém duas implementações de um programa em Python que simula uma bola quicando dentro de um hexágono giratório, com efeitos realistas de gravidade e atrito. O objetivo é comparar o desempenho e a abordagem de duas inteligências artificiais diferentes: DeepSeek R1 e ChatGPT 03-mini-high.

My own open source implementation of OpenAI's new Deep Research agent. Get the same capability without paying $200. You can even tweak the behavior of the agent with adjustable breadth and depth. Run it for 5 min or 5 hours, it'll auto adjust.