[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild

🦜🔗 Build context-aware reasoning applications

Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

🔍 A Hex Editor for Reverse Engineers, Programmers and people who value their retinas when working at 3 AM.

Lets make video diffusion practical!

Ray tracing and hybrid rasterization of Gaussian particles

An open protocol enabling communication and interoperability between opaque agentic applications.

10 Lessons to Get Started Building AI Agents

A real-time multifunctional Lidar SLAM package.

WhatsApp MCP server

Claude Desktop for Debian-based Linux distributions

RAI is an agentic framework for robotics, utilizing Langchain and ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.

ros2ai is a next-generation ROS 2 command line interface extension with LLMs

Make websites accessible for AI agents

This repo contains the python code as well as the webpage html files for the 4-LEGS project from VAILab at TAU.

A Collection of LiDAR-Camera-Calibration Papers, Toolboxes and Notes

🙌 OpenHands: Code Less, Make More

YouTube Music Desktop App bundled with custom plugins (and built-in ad blocker / downloader)

🚀 The fast, Pythonic way to build MCP servers and clients

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

[RAL 2023] A globally consistent LiDAR map optimization module

Define, Prompt and Test MCP enabled Agents and Workflows

Build effective agents using Model Context Protocol and simple workflow patterns