zilliztech — 7 Open-Source AI Agent Skills

zilliztech is the author of 7 open-source AI agent skills and MCP servers spanning mcp-server, claude-skill, codex-skill, agent-tool, with a combined 15,808+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 64/100) and security-graded — 7 verified safe.

Top skills by zilliztech

• claude-context — Code search MCP for Claude Code. Make entire codebase the context for any coding agent. (12.5k★ · quality 70/100 · security: safe)
• memsearch — A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus. (2.8k★ · quality 64/100 · security: safe)
• mcp-server-milvus — Model Context Protocol Servers for Milvus (246★ · quality 70/100 · security: safe)
• mfs — A context harness for AI agents: all your scattered context — code, memory, docs, databases, SaaS — in one searchable, browsable, file-like (158★ · quality 62/100 · security: safe)
• zilliz-mcp-server — A Model Context Protocol (MCP) server seamlessly connecting AI Agents and AI coding tools with Zilliz Cloud https://zilliz.com/ (35★ · quality 54/100 · security: safe)
• zilliz-plugin — Zilliz Cloud plugin for Claude Code & OpenAI Codex — manage clusters, collections, vector search, backups, and more through natural language (3★ · quality 74/100 · security: safe)
• milvus-skill — Agent skill that teaches LLMs to operate Milvus vector database using pymilvus — connection, collections, vector CRUD, search, hybrid se (1★ · quality 54/100 · security: safe)

View zilliztech on GitHub · Explore audited agent skills