The agent that generates working apps (and maybe some other things)

Like gmail for your coding agents. Lets various different agents communicate and coordinate with each other.

Simultaneous speech-to-text model

Implentations of simulation algorithms to be challenged by other methods in terms of simplicity, code size, performance and stability.

Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if you like it!

very good whiteboard SDK / infinite canvas SDK

cmux lets you run Claude Code, Codex CLI, Amp, Gemini CLI, Cursor CLI, Opencode, and other coding agent CLIs in parallel across multiple tasks

Libs to build OramaCore

Gridwise: WebGPU Compute Primitives in JavaScript

OramaCore is the AI runtime you need for your AI projects, answer engines, copilots, and search. It includes a fully-fledged full-text search engine, vector database, LLM interface, and many more u…

🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.

Embedded property graph database built for speed. Vector search and full-text search built in. Implements Cypher.

Browser-based user interface for Kuzu graph database

Visualize and analyze GitHub or local repositories using LLM-friendly summaries, file structure, and interactive dependency graphs.

Agent S: an open agentic framework that uses computers like a human

GPU-accelerated force graph layout and rendering

SIGGRAPH 2025 "Stable Cosserat Rods"

Python library for Agentic Document Extraction from LandingAI

Open-source personal bookmarks search engine

"Deep research for bugs" – Agentic root cause analysis through hypothesis-driven debugging

A quantitative trading system built with Rust.

Distance-Aware Pruned Graphs for Accurate and Efficient Approximate Nearest Neighbor Search (Submitted to VLDB 2026)

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning

Simulating embodied sensorimotor control with NeuroMechFly v2