hermes-agent

Q: How do I install hermes-agent?

Run npx skills add https://github.com/wihy/hermes-agent-skill --skill hermes-agent in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/hermes-agent/ (personal) or .claude/skills/hermes-agent/ (project).

by wihyAI & Agents

NousResearch Hermes Agent 通用集成 Skill。通过 CLI 调用 Hermes Agent 的核心能力： - 🚀 自改进技能系统（从任务中自动创建可复用技能） - 🧠 持久化记忆（FTS5全文搜索 + LLM摘要） - 🤖 子代理委托（任务隔离和并行处理） - 🔌 MCP 双向集成 - 🌐 浏览器自动化 - 💻 代码执行 - 🔍 网页研究 - 📦 完全可移植，支持任意 Claw/WorkBuddy 实例一键安装

Installs: 571
Last 24h: —
Trending rank: —
Security: Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/wihy/hermes-agent-skill --skill hermes-agent

01
Install
Run the command in your project. The CLI asks which agents to install for.
02
Describe the task
Ask your agent for something this skill covers. It loads hermes-agent automatically when relevant.
03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Hermes Agent Skill v2.0

概述

本 Skill 封装了 NousResearch Hermes Agent 的 CLI 调用能力，让 WorkBuddy/Claw 可以通过 Shell 命令利用 Hermes 的核心功能。

v2.0 改进：完全可移植，无硬编码路径，支持任意实例一键安装。

首次安装

一键安装（推荐）

当检测到 Hermes 未安装时，运行：

# 安装 Hermes Agent（自动克隆、创建虚拟环境、创建 CLI 入口）
bash ~/.workbuddy/skills/hermes-agent/scripts/install_hermes.sh

# 或自定义安装目录
bash ~/.workbuddy/skills/hermes-agent/scripts/install_hermes.sh --prefix ~/custom/path

安装脚本会自动：

✅ 检测 Python 3.11+ 环境
✅ 克隆 Hermes Agent 源码
✅ 创建 Python 虚拟环境并安装依赖
✅ 创建 ~/.local/bin/hermes CLI 入口
✅ 初始化 ~/.hermes/ 配置目录
✅ 生成默认 .env 配置模板

安装后配置 API Key

# 编辑配置文件，填入你的 API Key
nano ~/.hermes/.env

可选提供商（任选其一）：

# 智谱 AI（推荐国内用户）
GLM_API_KEY=your-key-here

# OpenRouter（支持多种模型）
OPENROUTER_API_KEY=sk-or-v1-your-key-here

# Anthropic
ANTHROPIC_API_KEY=sk-ant-your-key-here

# OpenAI
OPENAI_API_KEY=sk-your-key-here

验证安装

# 确认 PATH 包含 hermes
export PATH="$HOME/.local/bin:$PATH"
hermes --version

# 运行诊断
hermes doctor

迁移到其他 Claw 实例

将整个 Skill 目录复制到目标实例即可：

# 在目标实例上执行：
cp -r /path/to/hermes-agent ~/.workbuddy/skills/hermes-agent
bash ~/.workbuddy/skills/hermes-agent/scripts/install_hermes.sh
# 然后配置 API Key

核心工作流

1. 调用模式速查

场景	命令	说明
快速问答	`hermes run "问题" --non-interactive --no-stream`	最简调用
带上下文	`hermes run "问题" --context-file ./ctx.md --non-interactive`	注入项目上下文
子代理委托	使用 `scripts/hermes_delegate.sh`	复杂任务分解
技能查询	`hermes skills list`	查看已学技能
记忆搜索	`hermes memory search "关键词"`	检索历史知识
状态检查	`hermes status` 或 `hermes doctor`	诊断安装状态

2. CLI 命令完整参考

基础命令

# 启动交互式对话
hermes

# 单轮执行（WorkBuddy 集成首选）
hermes run "prompt" [选项]

# 非交互模式选项
--non-interactive    # 关闭交互式 TUI（必需）
--no-stream          # 禁用流式输出，返回完整结果
--context-file PATH  # 注入上下文文件
--toolset NAME       # 限制使用的工具集
--model MODEL        # 指定模型
--timeout SECONDS    # 超时时间（默认300秒）

子代理委托

# 通过 wrapper 脚本调用（推荐）
./scripts/hermes_delegate.sh \
  --task "分析竞品A和B的产品特性" \
  --tools "web_search,browser,file_write" \
  --timeout 300 \
  --output ./result.md

# 直接在 hermes run 中使用 delegate_task 工具
hermes run '使用delegate_task工具，任务是：分析XXX，工具限制：web_search,browser' \
  --non-interactive --no-stream

记忆管理

# 搜索历史记忆
hermes memory search "关键词"

# 查看所有笔记
hermes memory notes list

# 添加手动笔记
hermes memory notes add "重要发现：..."

# 导出/导入记忆
hermes memory export ./backup/
hermes memory import ./backup/

技能管理

hermes skills list                           # 列出所有技能
hermes skills create my-skill --description "描述"  # 创建新技能
hermes skills edit my-skill                  # 编辑技能
hermes skills remove my-skill                # 删除技能

插件管理

hermes plugins list                    # 列出插件
hermes plugins install user/repo       # 安装插件
hermes plugins enable/disable/update/remove plugin-name

定时任务 (Cron)

hermes cron list                       # 列出定时任务
hermes cron add --name "日报" --cron "0 9 * * *" --message "生成总结"
hermes cron pause/resume/remove TASK_ID

MCP 集成

hermes mcp serve --port 8080           # 启动 MCP Server
hermes mcp connect <server-config>     # 连接外部 MCP 服务

Wrapper 脚本

scripts/hermes_wrapper.sh

统一的 CLI 封装脚本，提供 JSON 格式化输出和错误处理：

./scripts/hermes_wrapper.sh [命令] [参数...]

# 示例
./scripts/hermes_wrapper.sh run "分析内容" --timeout 60
./scripts/hermes_wrapper.sh memory search "关键词"
./scripts/hermes_wrapper.sh status

输出格式：JSON（包含 success, output, error, duration_ms 字段）

scripts/hermes_delegate.sh

子代理委托专用脚本：

./scripts/hermes_delegate.sh --task "任务描述" [选项]

# 可选选项
--tools "tool1,tool2"      # 限制可用工具集
--timeout 300              # 超时时间（秒）
--output ./result.md        # 输出文件路径
--max-concurrent 3         # 最大并发数（默认3）
--context-file ./ctx.md     # 额外上下文文件
-v                         # 详细输出

scripts/install_hermes.sh

一键安装脚本（详见上方「首次安装」章节）：

bash scripts/install_hermes.sh [--skip-deps] [--prefix DIR]

模型配置

运行交互式配置向导：

hermes model

或直接编辑 ~/.hermes/config.yaml：

model:
  provider: zai           # 可选: openrouter, anthropic, openai, zai, gemini 等
  default: "glm-5"        # 默认模型
  base_url: "https://api.z.ai/api/paas/v4"  # 自定义 API 地址

支持的提供商：openrouter, anthropic, openai, gemini, zai, kimi-coding, nous, custom

最佳实践

✅ 推荐做法

始终使用 --non-interactive --no-stream：避免 TUI 阻塞
设置合理的超时时间：简单任务 60s，复杂任务 300s
限制工具集：用 --toolset 减少 Token 消耗
使用上下文文件：将大段背景信息放入文件，而非 prompt 中
错误重试机制：网络问题时自动重试 1-2 次

⚠️ 注意事项

Token 成本：每次调用都有成本
并发限制：最多 3 个并发子代理
超时保护：长时间运行的任务必须设置 timeout
API Key 安全：不要在 Skill 文件中硬编码密钥
Python 版本：确保使用 Python 3.11+

故障排除

问题	解决方案
`command not found: hermes`	运行 `export PATH="$HOME/.local/bin:$PATH"` 或重新执行 `install_hermes.sh`
`TypeError: unsupported operand`	确保 Python 3.11+
API Key 错误	检查 `~/.hermes/.env` 配置
连接超时	检查网络，或更换 LLM 提供商
子代理失败	减少 `--max-concurrent` 或增加 `--timeout`
安装脚本失败	运行 `hermes doctor` 诊断

文件结构

hermes-agent/
├── SKILL.md                    # 本文件（Skill 说明文档）
├── _meta.json                  # Skill 元数据（可移植性声明）
├── scripts/
│   ├── install_hermes.sh       # 一键安装脚本（通用）
│   ├── hermes_wrapper.sh       # 统一 CLI 封装（动态路径检测）
│   └── hermes_delegate.sh      # 子代理委托脚本（动态路径检测）
└── references/                 # 参考文档

更新日志

v2.0.0 (2026-04-12): 完全可移植版 — 移除所有硬编码路径，添加一键安装脚本，支持任意 Claw 实例迁移
v1.0.0 (2026-04-11): 初始版本，支持基础 CLI 调用、子代理委托、记忆/技能管理

FAQ

What does the hermes-agent skill do?

How do I install hermes-agent?

Run npx skills add https://github.com/wihy/hermes-agent-skill --skill hermes-agent in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/hermes-agent/ (personal) or .claude/skills/hermes-agent/ (project).

Which AI agents can use hermes-agent?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is hermes-agent safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains hermes-agent?

It is published by wihy in wihy/hermes-agent-skill. It has 571 recorded installs.

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs

hermes-agent

Install

Install

Describe the task

Review the result

SKILL.md

Hermes Agent Skill v2.0

概述

首次安装

一键安装（推荐）

安装后配置 API Key

验证安装

迁移到其他 Claw 实例

核心工作流

1. 调用模式速查

2. CLI 命令完整参考

基础命令

子代理委托

记忆管理

技能管理

插件管理

定时任务 (Cron)

MCP 集成

Wrapper 脚本

scripts/hermes_wrapper.sh

scripts/hermes_delegate.sh

scripts/install_hermes.sh

模型配置

最佳实践

✅ 推荐做法

⚠️ 注意事项

故障排除

文件结构

更新日志

FAQ

Popular ai & agents skills

google-agents-cli-publish

google-agents-cli-eval

skill-creator

codex-pet

full-output-enforcement

executing-plans