Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add znlgis/opengis-skills --skill hermes-agentgit clone --depth 1 https://github.com/znlgis/opengis-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/znlgis/opengis-skills/hermes-agent)<a href="https://agentmods.dev/skills/znlgis/opengis-skills/hermes-agent"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/hermes-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/znlgis/opengis-skills/hermes-agent"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/hermes-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.01800 |
| Opus 5 | $0.00023 | $0.00900 |
| Sonnet 5 | $0.00009 | $0.00360 |
| Haiku 4.5 | $0.00005 | $0.00180 |
Grade C, and why
hermes-agent scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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） 最新版本： 参见 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：
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 不直接支持，请安装 WSL2 后在 WSL 内执行 Linux 流程。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）：
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
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。
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
hermes setup # 初始化配置
hermes model # 选择/配置模型
hermes chat # 开始对话
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。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 158 lines · 46 tokens per session scan C 44dd48ec5b1d
hermes-agent is a skill published in the GitHub repository znlgis/opengis-skills (60 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 1,800 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
memmachine-memory
Use when an agent or model needs durable project, user, or session context from MemMachine, needs to save information to MemMachine memory, has requests involving mem-cli, memmachine, or memmachineclient, has insufficient conversation context, or is tempted to search local files for prior context that should come from…
memori-mcp-usage
Use when an MCP-connected agent should use Memori tools for targeted recall, summaries, post-compaction briefs, durable memory augmentation, quota checks, signup, feedback, preferences, prior context, or cross-session continuity.
memori
You have access to Memori, agent-native memory infrastructure: an LLM-agnostic layer that structures memory from not just natural language, but also from agent trace that comes from execution.
memori
Ambient Memori long-term memory for Claude Code via local Bash. MUST TRIGGER on essentially every non-trivial user turn: run recall before drafting any substantive response, whether or not the user mentioned memory, a prior session, or past work. The default is to check memory first; do not wait to be asked. Always…
memori
Agent-native memory for OpenClaw that structures memory from agent trace, execution history, decisions, tool calls, and conversations into durable long-term memory primitives.
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.