Stars
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
An Agent Skill for designing cross-platform desktop apps that feel native — distilled from Raycast's 2.0 deep-dive and reverse engineering of Raycast Beta.app. Eight architectural tenets, four-laye…
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
Harness engineering beginner tutorial, from 0 to 1
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
An Agent Skill helping you to optimize Xcode incremental and clean builds by running benchmarks and optimizing build settings.
The agent that grows with you
The best-benchmarked open-source AI memory system. And it's free.
Battle-tested Claude Code skills for modern xOS (iOS, iPadOS, watchOS, tvOS) development
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
🛠️ Awesome tools & guides for harness engineering.
purpose of this repo is to Implement LLMOPs as shared in Deeplearning AI course
tmux config with built-in terminal automation and agent-to-agent communication.
Cloudflare Workers email inbox with token-protected API. Catch-all receiving, full-text search, and AI agent skill included.
A Cloudflare-based email service | 基于 Cloudflare 的邮箱服务 | Cloudflare Email 邮箱 Mail
AI agents running research on single-GPU nanochat training automatically
onevcat / Prowl
Forked from supabitapp/supacodenative macOS codings agent orchestrator
React debug inspector for component locating and source jump
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
A Claude Code skill that 10x's your effective context window by dispatching tasks to background AI workers.
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
🚀 Expert guidance for HarmonyOS NEXT (API 12+) development. Covers IDE operations, performance tuning, architecture (HAP/HAR/HSP), and automation testing.
Lightweight, open-source AI agent for your tools, chats, and workflows.
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
An agentic skills framework & software development methodology that works.
A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
This guide is designed for OpenClaw itself (Agent-facing), not as a traditional human-only hardening checklist.