Use agents as the map layer, not the whole directory.
Start from the tool category, then open an Agent page to see which Skills, MCP servers, CLI tools, and Workflows fit that execution surface.
Choose the surface you work in.
Each Agent page is a compatibility sheet: capabilities, official sources, mapped tools, and related learning pages.
CodeGeeX
A China-origin IDE coding assistant focused on completion, explanation, and editor-side developer assistance.
Kimi CLI / Kimi Agent
Moonshot AI's Kimi agent surface for long-context research, document-heavy workflows, and Kimi Code CLI development tasks.
Qwen Code
Alibaba Qwen's open-source coding-agent and agent-framework path for CLI coding, MCP-connected tools, function calling, and Qwen-native workflows.
Trae
ByteDance's AI IDE agent surface for project coding, rules-guided behavior, MCP integrations, and Chinese developer workflows.
Claude Code
Anthropic's terminal-native coding agent for large repositories, MCP-connected tools, skills, hooks, and team workflows.
Codex
OpenAI's coding agent for repository implementation, review, verification, and tool-assisted engineering work.
Cursor
An editor-first AI coding environment with agentic IDE workflows, rules, memories, MCP, and cursor-agent CLI support.
Hermes Agent
Nous Research's open-source, terminal-oriented agent with skills, MCP integration, local execution, and a large Skills Hub ecosystem.
OpenClaw
A high-signal open agent ecosystem centered on local gateway architecture, skills, plugins, tools, MCP, and community extension review.