The world's most flexible commerce platform.

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

A High-Performance, Asynchronous Litecoin Address Generator and Balance Checker Built With Modern Python Practices and Professional-Grade Architecture.

Wideband passive Meshtastic LoRa receiver with multi-station fusion and offline PSK recovery

A vector index built on TurboQuant, written in Rust with Python bindings

Proxmox VE Helper-Scripts (Community Edition)

aider is AI pair programming in your terminal

A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators.

SPIR-🇹: shader-focused IR to target, transform and translate from 🦀

Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.

Kilo is a multi-cloud network overlay built on WireGuard and designed for Kubernetes (k8s + wg = kg)

Official repository for paper "LaTo: Landmark-tokenized Diffusion Transformer for Fine-grained Human Face Editing"

Network monitoring & diagnosis suite for Kubernetes

OpenTelemetry Compile-Time Instrumentation for Golang

Official repository for ICML 2026 paper "Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization"

A CLI evaluation framework to make your Agent Skill Up.

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

Paimon-cpp is a high-performance C++ implementation of Apache Paimon.

A lightweight, lightning-fast, in-process vector database

Secure, Fast, and Extensible Sandbox runtime for AI agents.

Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

Self-hosted AI workspace.

EvoSkill — An open-source framework that automatically discovers and synthesizes reusable agent skills from failed trajectories to improve coding agent performance.

TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.

Optimized primitives for collective multi-GPU communication

Ongoing research training transformer models at scale

A framework for quantitative finance In python.

Drop-in prompt-caching fixes for the LLM agent harness you use. Point your AI coding agent at this repo and it ships the patches.

A unified inference and post-training framework for accelerated video generation.