Art & Design

Go SDK for building Gibson agents, tools, and plugins

CLI tools for Claude Code — Twitter, Google Workspace, Image Generation

Practical macOS dotfiles for keyboard-driven workspaces, a compact desktop UI, terminal tools, and local AI prompt/agent workflows.

Build Anthropic SDK apps with cost tracking, policy checks, and agent tools in one Python framework

Build paid APIs, agents, tools, and data feeds on the DNA x402 hosted rail

CubePi — An async-first Python agent kernel inspired by Pi, built for coding agents, tools, and continuous sessions.

Curate and explore a comprehensive list of Chinese AI agents, tools, and resources for development and research in artificial intelligence.

Anvia is a TypeScript runtime for building provider-agnostic agents, tool workflows, and structured extraction inside your application code.

An advanced Artificial Intelligence (AI) example of a Retrieval-Augmented Generation (RAG) Next.js web app with agents (tools)

AI-powered analytics platform that transforms natural language business questions into SQL queries, statistical insights, interactive visualizations, and executive reports using LLMs, RAG pipelines, and agentic workflows. Built with FastAPI, PostgreSQL, AI agents, and production-grade MLOps practices.

End-to-end Microsoft Foundry agent reference: in-process Agent Framework agents, Foundry hosted agents, PromptAgents, multi-agent workflows with HITL, Fabric Data Agent + Databricks integration, React ops dashboard. One-command azd up deploy.

Hands-on projects and experiments focused on building AI agents, workflow automation, and intelligent systems using n8n, AI, RAG, and related technologies.

TinyFlow is a lightweight, extensible, and provider-agnostic Python framework for building LLM agents. It provides a clean abstraction layer over major LLM providers (OpenAI, Anthropic, Gemini), embedding models, and vector databases, enabling you to build complex agentic workflows with ease.

Aurelius: frontier-tier agentic LLM platform | 1.4B transformer | 146 build cycles | 25265+ tests | Python 3.14 | MCTS reasoning, BM25+hybrid search, agentic tools, multimodal, MCP, deployment | security-hardened: 0 open HIGH/CRITICAL findings

Explore Claude Code's Agent Harness architecture with a clear breakdown of its runtime, tools, and control flow for AI agent builders

LangGraph is an open-source framework from LangChain for building stateful, multi-actor agent workflows with low-level primitives for greater control over agent behavior. LangGraph Platform (LangSmith Deployment) provides managed infrastructure for running agents in production with assistants, threads, and runs.

🤖 Build efficient multi-agent workflows with the OpenAI Agents SDK, supporting OpenAI APIs and 100+ other LLMs for flexible solutions.

Visible multi-agent CLI teams for Claude, Codex, Gemini, OpenCode, and Droid with project memory and tmux supervision

Claude Code skill: mandatory security baseline for external content (WebFetch, WebSearch, GitHub reads). Defends against prompt injection, PII leaks in URLs, unwanted downloads (npm/pip/git clone), and license violations when reusing repo patterns. Auto-runs a 6-step setup wizard. Bilingual triggers (EN/DE). CC-BY-4.0.

Build Agent Banking Platform UI for managing whole agents, tools, workflows

Build and manage Claude agent workflows with a TypeScript and SvelteKit app for structured AI automation and local SQLite storage

Build a runtime for Claude Code with persistence, observability, and multi-process coordination for long-running AI agents

Automate Claude Code, Gemini CLI, and Codex in tmux sessions to reuse terminal auth and read AI output from scrollback

通用角色与场景设计技能包：角色资产、身高比例锁、三视图一致性、服装状态、道具锚点、场景动线与 AI 图像/视频提示词流程