Better UI app for running code agents in parallel (ClaudeCode, OpenCode, Codex)

Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports local and cloud LLMs (Ollama, Google, Anthropic, ...). Searches 10+ sources - arXiv, PubMed, web, and yo…

a project brain for your AI. Give LLMs instant architectural context without burning tokens

Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

Depth Anything 3

SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility.

Run SwarmUI as a serverless API on RunPod

Personal AI Notebooks. Organize files & webpages and generate notes from them. Open source, local & open data, open model choice (incl. local).

RTAB-Map library and standalone application

Automated multimedia storytelling using advanced AI models. Create rich narratives, stunning visuals, voiceovers, and videos effortlessly.

DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top-level planning agent to coo…

[CVPR 2025 Highlight] Real-time dense scene reconstruction with SLAM3R

A delightful chore manager that allows you to give out points for chores completed for every member of your family (android)

Rates of successful conceptions according to COVID-19 vaccination status: Data from the Czech Republic

AWS HealthScribe allows you to automatically create clinical notes from patient-clinician conversations using generative AI. This art-of-the-possible demo allows you to interact with AWS HealthScri…

A web-based polygon drawing tool built with Konva.js to measure dimensions, calculate areas, apply scales, and save or reload sketches.

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Provide an SDK for quickly integrating ComfyUI workflows into web applications. 用于web应用的快速接入comfyui工作流，提供sdk

A real-time, direct and tightly-coupled LiDAR-Inertial SLAM for high velocities with spinning LiDARs

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

All the hardware needed to build your own OS3M Mouse!