agency-agents-zh vs Graft
agency-agents-zh: agency-agents-zh is the Chinese community edition of agency-agents, with 328 ready-to-use AI expert roles across 22 departments: 261 translated from upstream and 67 original roles for the Chinese market such as Xiaohongshu, Douyin, WeChat and Feishu operations. An install script copies them into 20 tools including Claude Code, Cursor, Copilot, Kiro, Trae and OpenClaw.; Graft: Graft is an open-source context layer designed to accelerate and optimize coding agents like Claude Code, Cursor, and Gemini by providing deep contextual understanding of large codebases. It builds a human-readable code graph and linked markdown nodes, enabling agents to operate faster, cheaper, and with higher correctness by avoiding repeated code exploration.
TL;DR
Adding Chinese-language specialist subagents to Claude Code
- You want to generate a readable, interconnected Markdown knowledge graph of your repository so coding agents (Claude Code, Cursor) can grep and explore without expensive re-indexing.
- You want to reduce context token waste by giving agents precise map-like documentation of modules and call paths.
- You need an enterprise graph database with semantic vector embeddings and Cypher queries; code-graph-rag with Neo4j fits that scale.
- You only have a small, single-file script or a trivial repository.
Side-by-Side Comparison
agency-agents-zhGraftFeatures
agency-agents-zhGraftUse Cases
agency-agents-zhGraftBest For
agency-agents-zhGraftFAQ
Deploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.