Search awesome repositories

Blackbox prober exporter

Raw browser/feature support data from caniuse.com

Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

Search everywhere and in a hurry!

A treasure chest for visual classification and recognition powered by PaddlePaddle

Python Classes Without Boilerplate

Open-source engine for Heroes of Might and Magic III

Build and deploy AI Agents on Cloudflare

JanusGraph: an open-source, distributed graph database

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

A simple, distributed task scheduler and runner with a web based UI.

Modern concurrency tools including agents, futures, promises, thread pools, supervisors, and more. Inspired by Erlang, Clojure, Scala, Go, Java, JavaScript, and classic concurrency patterns.

(Replaces Next.js/Nuxt) 🔨 Build mission-critical applications with stability and development freedom.

A lightweight, secure, and feature-rich Discord terminal (TUI) client.

SWE-bench: Can Language Models Resolve Real-world Github Issues?

Democratizing Reinforcement Learning for LLMs

SSH2 client and server modules written in pure JavaScript for node.js

PyTorch native post-training library

Apache Maka (Incubating) is a high-performance agent workspace that keeps a complete record of everything it did.

CUDA accelerated rasterization of gaussian splatting

Gemma open-weight LLM library, from Google DeepMind

MimiClaw: Personal Agent on a $5 chip. No OS(Linux). No Node.js. No Mac mini. No Raspberry Pi. No VPS. Hardware agents OS. On device Muse.

Enterprise-Grade OSS PostgreSQL Distribution with HA, PITR, IaC, Monitor, 12 kernel forks and 575 PG extensions. Best-of-breed products integrated as a platform. Self-host Postgres like a Pro!

Open-Source Subscription Billing & Payments Platform

tap-producing test harness for node and browsers

An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.

A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

Just like TextEdit on Mac but dedicated to Markdown.

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.