Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

Triton language and compiler for Ascend NPU

Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plans that survive context loss and /clear, plus a deterministic completion gate and multi-a…

Tesla Mod — Flipper Zero & ESP32. Nag killer, FSD region unlock, track mode, BMS dashboard, blind spot alert, high beam strobe, speed display, steering mode + more. Works via OBD-II or X179 connector.

LLM驱动的 A/H/美股智能分析：多数据源行情 + 实时新闻 + LLM决策仪表盘 + 多渠道推送，零成本定时运行，纯白嫖. LLM-powered stock analysis system for A/H/US markets.

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

Claude Code Channel plugin for WeChat — bridge WeChat messages into Claude Code sessions via the official ClawBot ilink API

😼 优雅地使用基于 clash/mihomo 的代理环境

instruments for Agent

这是一个简单的技术科普教程项目，主要聚焦于解释一些有趣的，前沿的技术概念和原理。每篇文章都力求在 5 分钟内阅读完成。

This is the official **live** mirror of Ascend-native hardware plugin for ray

Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Github mirror of trition-lang/triton repo.

🚀 Efficient implementations for emerging model architectures

Puzzles for learning Triton

torchcomms: a modern PyTorch communications API

A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.

Ascend TileLang adapter

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

JittorInfer is a high-performance C++ inference framework designed for large language models on Huawei's Ascend AI processor.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

⚡️IPTV直播源自动更新平台『🤖全自动采集、筛选、测速、生成🚀』：自定义获取频道；IPv4/IPv6；接口验效；推流；多平台支持；工作流、Docker、命令行、GUI多端部署 | IPTV live streaming source automatic update platform

Woodpecker is a simple, yet powerful CI/CD engine with great extensibility.