菜单
MiniMax Agent Platform (agent.minimax.io) — MaxHermes, MaxClaw, Skills marketplace. Relacao com Hermes Agent (NousResearch) e OpenClaw.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | minimax-agent-platform |
| description | MiniMax Agent Platform (agent.minimax.io) — MaxHermes, MaxClaw, Skills marketplace. Relacao com Hermes Agent (NousResearch) e OpenClaw. |
| category | ai-platforms |
Plataforma de agentes de IA da MiniMax. Disponibiliza agentes autonomos MaxHermes e MaxClaw alimentados pelo modelo MiniMax-M2.7. Acesso via web, Telegram, Discord, Slack.
Tagline: "An Agent That Grows With You" Modelo: MiniMax-M2.7
Caracteristicas:
Tagline: "Your 24/7 personal assistant" Modelo: MiniMax M2.7
Caracteristicas:
MAXCLAW e baseado em OpenClaw — fork open-source que por sua vez derivou do Hermes Agent (NousResearch).
MAXHERMES usa o nome "Hermes" por branding — mas e uma implementacao proprietaria da MiniMax sobre a mesma arquitectura.
OpenClaw (open-source, comunidade)
fork
Hermes Agent (NousResearch) — github.com/NousResearch/hermes-agent
fork
MaxHermes + MaxClaw (MiniMax) — agent.minimax.io
URL: https://agent.minimax.io/skills
Sistema de capacidades modulares instalveis. Categorias: By MiniMax, User Contributions.
Skills populares:
Agentes pre-configurados por dominio:
API Endpoints (confirmado 30/04/2026):
https://api.minimaxi.com/v1https://api.minimaxi.com/anthropicModel Context Windows:
| Modelo | Context Window |
|---|---|
| MiniMax-M2.7 | 204,800 tokens |
| MiniMax-M2.7-highspeed | 204,800 tokens |
| MiniMax-M2.5 | 204,800 tokens |
| MiniMax-M2.1 | 204,800 tokens |
IMPORTANTE: Nao existe modelo MiniMax com 1M de contexto. Rumores sobre isso sao incorretos.
O nosso Hermes Agent (em ~/.hermes/hermes-agent/) e a mesma arquitectura que MaxHermes/MaxClaw. A diferenca:
~/.hermes/skills/ — equivalente ao marketplaceTransforms the Hermes agent from a reactive question-answerer into a proactive autonomous executor. ARCHITECT takes any high-level goal, decomposes it into a dependency-aware task graph, executes each step with validation, self-corrects on failure, and delivers results — all without hand-holding. The missing execution layer for personal AI agents. Zero dependencies. Zero config. Works with any model. Pairs with apex-agent and agent-memoria for the complete autonomous agent stack.
Auto-reflective self-improvement skill — extracts learnings from corrections and success patterns, permanently encodes them into memory and skills. Philosophy: Correct once, never again.
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.
Integrate existing autonomous agents (like Hermes) into multi-agent orchestration platforms (AionUI, LangChain, etc.) via ACP over stdio.
Paperclip AI agent operations — creating agents with hierarchy, autonomous operation via hierarchical issues, and troubleshooting. Use when: creating agents, setting up org hierarchy, recovering from errors, or monitoring agent health.
Paperclip AI orchestration CLI — authentication, API usage, and self-hosted setup