Hermes Agent

Q: Why use Hermes Agent on TypingMind?

Because you install it once and use it with any model. Hermes Agent is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

Q: How do I install Hermes Agent in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/znlgis/opengis-skills/tree/main/ai/hermes-agent. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Q: Which AI models can use Hermes Agent?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

Q: How many AI models can I use with Hermes Agent?

As many as you like. As long as a model supports skills, you can use Hermes Agent with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Q: Is the Hermes Agent AI skill free?

Yes. It is published on GitHub by znlgis under the MIT license. You only pay your own AI provider for the tokens you use.

Q: What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

Q: How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Community

znlgis

hermes-agent

Use when you want a terminal agent that learns from experience — hermes setup/model/tools/doctor, skills + persistent memory + session search, hermes gateway for Telegram/Discord/Slack/WhatsApp/Signal, hermes cron create for scheduled jobs, MCP and subagents; also for `hermes: command not found` after install.sh, Python 3.15 unsupported-engine errors, and Windows users wrongly told to use WSL2. Hermes Agent (Nous Research), Python 3.11-3.14.

Overview

Publisher	znlgis
Repository	`opengis-skills`
Skill name	`hermes-agent`
Stars	76
Forks	12
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by znlgis on GitHub. Read the source before you install it.

Installation

Install the Hermes Agent AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/znlgis/opengis-skills/tree/main/ai/hermes-agent
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/znlgis/opengis-skills.git /tmp/opengis-skills
mkdir -p .claude/skills
cp -r /tmp/opengis-skills/ai/hermes-agent .claude/skills/hermes-agent

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hermes Agent in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Hermes Agent on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Hermes Agent is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

项目地址： https://github.com/NousResearch/hermes-agent

官网 / 文档： https://nousresearch.com/ ｜ https://hermes-agent.nousresearch.com/docs

许可证： MIT ｜ 语言： Python（3.11 – 3.14，requires-python = ">=3.11,<3.15"）

最新版本： v0.22.5（2026-10-23 发布，实测 releases/latest 重定向；见 GitHub Releases）

概述

Hermes 是「The agent that grows with you」——唯一内置完整学习闭环的开源 Agent。它不是 IDE 插件或单一模型封装，而是一套完整的 Agent Harness：

自学习闭环：使用中自主创建技能（skills）、在使用时改进技能、把关键事实写入持久化记忆、检索自己的历史会话，并对用户建立越来越精确的画像。
终端优先：CLI/TUI（hermes）交互，命令如 hermes setup、hermes model、hermes tools、hermes config、hermes doctor。
模型无关：支持多 Provider 与模型配置体系。
工具系统 + 终端后端：执行命令、读写文件等。
MCP 集成与上下文文件。
消息网关：多平台接入（Telegram 等），可一边在聊天里对话一边让它在云端 VM 干活。
定时任务 / 自动化、语音/视觉/浏览器、子代理协作、插件开发。
部署灵活：5 美元 VPS、GPU 集群，或 Daytona / Modal 等空闲近零成本的 Serverless。

安装

支持 Linux、macOS、WSL2、Termux（Android）、Nix。一键脚本：

bash
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
# 脚本会准备 Python 环境，并在 ~/.hermes/hermes-agent/ 下执行 uv pip install -e ".[all]"

source ~/.bashrc      # 或 source ~/.zshrc
hermes                # 进入 TUI

Windows 自 v0.22 起原生支持（CLI、gateway、TUI、工具均可直接跑，无需 WSL2）；仍可用 WSL2 走 Linux 一键脚本。Termux 默认安装 .[termux] 子集（跳过尚未测试的浏览器与 WhatsApp 部分）。

手动 / 开发安装（uv）：

bash
git clone https://github.com/NousResearch/hermes-agent.git
cd hermes-agent
curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv venv --python 3.11
uv pip install -e ".[all,dev]"
./hermes               # 直接运行（无需手动 source venv）

初始化与核心命令

bash
hermes setup     # 首次初始化（账户、目录、基础配置）
hermes model     # 选择 Provider 与模型
hermes tools     # 配置每个平台启用哪些 toolset
hermes config    # 编辑配置
hermes doctor    # 体检 / 排错

自学习闭环（核心特性）

Hermes 区别于普通 Agent 的关键在于「学习」：

技能(Skills)：把成功的做法沉淀为可复用技能；后续遇到类似任务自动调用并持续改进。
记忆(Memory)：把重要事实持久化，跨会话保留；它会「提醒自己」去固化知识。
历史检索：能搜索自己过去的对话，复用上下文与结论。
用户画像：跨会话累积，对「你是谁、偏好什么」建立越来越准的模型。
可选 Honcho 记忆 Provider：接入 plastic-labs/honcho 做辩证用户建模（dialectic user modeling），把零散事实提炼为动态用户画像；仓库内置 plugins/memory/honcho/ 实现，执行 uv pip install -e ".[honcho]" 后以 hermes plugins enable memory:honcho 启用。

这意味着 Hermes 越用越「懂你」，适合作为长期个人/团队助手，而非一次性任务工具。

典型工作流

工作流一：快速上手

bash
hermes setup      # 初始化配置（向导）
hermes model      # 选择/配置 Provider 与模型
hermes            # 不带子命令直接启动终端 TUI

创建第一个技能：让 Hermes 监听你的工作 → 自动总结模式 → 写入技能文件。之后可用 hermes skills list 查看、hermes memory 管理记忆。

工作流二：长期运行部署

bash
# 启动消息网关（Telegram / Discord / Slack / WhatsApp / Signal 共用同一 gateway 进程）
hermes gateway

# 定时任务：schedule 支持 "30m" / "every 2h" / cron 表达式
hermes cron create "0 9 * * *" "汇总昨天的提交并生成晨报" --name daily-brief --deliver telegram
hermes cron list --all

hermes serve 是无界面的 Web/API 服务（--host / --port / --stop / --status），不是消息网关；旧文档里的 hermes serve --gateway telegram 已不存在。定期审查 ~/.hermes/memories/ 和 ~/.hermes/skills/ 确保记忆质量。

工作流三：团队协作

配置 MCP 集成 → 连接外部工具与数据源
设置子代理 → 分配专门任务给子代理
审查子代理产出 → 合并到主上下文

进阶能力

能力	说明
模型供应商与配置	多 Provider，统一配置体系（`hermes model` / `hermes config`）
工具系统与终端后端	命令执行、文件读写等；按平台启用 toolset
MCP 集成	接入 MCP server 扩展外部工具；配合上下文文件注入项目知识
消息网关	多平台接入，远程对话与云端执行解耦
定时任务	cron 式自动化
语音 / 视觉 / 浏览器	多模态与网页操作
子代理协作	拆解复杂任务并行处理
插件开发	扩展自定义能力与研究功能

常见问题（FAQ）

问题	解决
安装失败	确认 Python ≥ 3.11；脚本依赖 `uv`，可先手动装 uv 再 `uv pip install -e ".[all]"`
Windows 能跑吗	能，v0.22+ 原生支持（CLI/gateway/TUI/tools）；老教程要求 WSL2 已过时，WSL2 仍可选
`pip install` 报 `Requires-Python >=3.11,<3.15`	用 Python 3.11–3.14 建 venv；3.15 尚未支持
`hermes serve --gateway` 报无法识别参数	`serve` 只起 Web/API 服务；消息网关用 `hermes gateway`
`hermes` 安装后不在 PATH	`install.sh` 会把 `~/.local/bin` 写入 shell rc；重开终端或 `source ~/.bashrc`，Termux 用 `~/bin`
Android 部分功能缺失	Termux 默认装 `.[termux]` 子集（跳过浏览器/WhatsApp），按官方 Termux Guide 手动补齐
选不到模型	先 `hermes model` 配置 Provider 与 API Key；`hermes doctor` 排错
它“记住”的东西在哪	持久化记忆/技能存于 Hermes 主目录（`~/.hermes/` 或 `$HERMES_HOME`）
想接私有工具	通过 MCP 集成接入，并在 `hermes tools` 中启用

AI 使用建议

用户提到「自学习 / 会成长的 AI Agent」「Nous Research Hermes」「带记忆和技能闭环的终端 Agent」时加载本技能。
强调其差异点：学习闭环（技能+记忆+历史+用户画像），而非普通工具调用框架。
安装走官方 install.sh（Linux/macOS/WSL2/Termux/Nix），用 hermes setup/model/tools/doctor 完成初始化与排错。
复杂任务建议用子代理协作 + MCP 扩展；长期使用价值来自记忆与技能的持续积累。

参考资源

文档：https://hermes-agent.nousresearch.com/docs
Nous Research：https://nousresearch.com/
上游中文教程：https://znlgis.github.io/（ai/hermes-agent 系列）

Frequently asked questions

What does the Hermes Agent AI skill do?

Why use Hermes Agent on TypingMind?

Because you install it once and use it with any model. Hermes Agent is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Hermes Agent in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/znlgis/opengis-skills/tree/main/ai/hermes-agent. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Hermes Agent?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Hermes Agent?

As many as you like. As long as a model supports skills, you can use Hermes Agent with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Hermes Agent AI skill free?

Yes. It is published on GitHub by znlgis under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Doc Coauthoring

anthropics

OrganizationPopular

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This…

Caveman Discover

Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.

Complain

Autonomously yeet a brief, unstructured complaint about agent tooling or doing agent work. Preserve the raw voice. Submit proactively without permission, preview, or announcement, then continue the…

Contact Widget

Self-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies.

Hermes Agent

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

概述

安装

初始化与核心命令

自学习闭环（核心特性）

典型工作流

工作流一：快速上手

工作流二：长期运行部署

工作流三：团队协作

进阶能力

常见问题（FAQ）

AI 使用建议

相关技能

参考资源

Frequently asked questions

Set up your own AI workspace now

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

概述

安装

初始化与核心命令

自学习闭环（核心特性）

典型工作流

工作流一：快速上手

工作流二：长期运行部署

工作流三：团队协作

进阶能力

常见问题（FAQ）

AI 使用建议

相关技能

参考资源

Frequently asked questions

Related AI Skills

Set up your own AI workspace now