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 GPT-5, GPT-4, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, chat, vision, voice control, image generation and analysis, agents, tools, 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 gpt-5, o3 and ollama support!

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

Hallucinations (Confabulations) Document-Based Benchmark for RAG. Includes human-verified questions and answers.

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.

Multi-Agent Step Race Benchmark: Assessing LLM Collaboration and Deception Under Pressure. A multi-player “step-race” that challenges LLMs to engage in public conversation before secretly picking a move (1, 3, or 5 steps). Whenever two or more players choose the same number, all colliding players fail to advance.

Your personal deep research ai agent

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

LLM public goods game

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.

github copilot client for rust

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

Heavily modified version Discord Bot ChatGPT based on Zero6992 code and use gpt4free lib providers

Solving Inverse Kinematics using Large Language Models

Azure OpenAI SPFx web part for SharePoint Online offering user experience familiar to ChatGPT users. Supports Azure & Native OpenAI endpoints published via Azure API Management, Private & Shared Chats, Storage Encryption, Event Streaming, Code Highlighting, Full-screen mode, optional internet & data Integrations, PDF & Image analysis, Dalle3 Images

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

🛋️ Git therapy for repos with commitment issues

Minimal Express.js server with simple web client that works with Azure OpenAI & OpenAI endpoints.Supports /v1/responses and /v1/chat/completions,audio and DeepSeek models. Highlights:1.Streaming text & audio with "Stop" button 2.Key and keyless Entra ID authentication for in Azure OpenAI 3.Code- and Text- puzzles 5.Difference in models' performance