# 使用 Homebrew, winget, apk, dnf 安装 hermes-agent

查看 hermes-agent 的安装路径、可执行文件、元数据以及面向 AI 代理工作流的安全说明。

## 安装

```sh
sudo av install brew:hermes-agent
```

其他安装命令:

### macOS

- Homebrew (100%):

```sh
brew install hermes-agent
```

  证据: local Homebrew formula metadata

### Linux

- apk (92%):

```sh
sudo apk add hermes
```

  证据: Alpine Linux edge package indexes: hermes from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz

- dnf (92%):

```sh
sudo dnf install Hermes
```

  证据: Fedora Rawhide package metadata: Hermes from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/210a2053c8e007daf9ae39c2a21daaed9b2ddd07d63ecffa597050361e73650c-primary.xml.zst

### Windows

- winget (92%):

```sh
winget install --id fathah.HermesDesktop -e
```

  证据: Windows Package Manager source index: fathah.HermesDesktop from https://cdn.winget.microsoft.com/cache/source.msix

## 软件包事实

- **软件包键:** brew:hermes-agent
- **软件包管理器:** Homebrew
- **软件包管理器页面:** <https://formulae.brew.sh/formula/hermes-agent>
- **版本:** 2026.7.20
- **来源摘要:** Self-improving AI agent that creates skills from experience
- **主页:** <https://hermes-agent.nousresearch.com>
- **仓库:** <https://github.com/NousResearch/hermes-agent>
- **上游文档:** <https://hermes-agent.nousresearch.com>
- **许可证:** MIT
- **源码归档:** <https://github.com/NousResearch/hermes-agent/archive/refs/tags/v2026.7.20.tar.gz>
- **最后更新:** 2026-08-03T21:25:38+02:00
- **已生成:** 2026-08-04T22:13:35+00:00

## 可执行文件

- hermes (cli)
- hermes-acp (cli)
- hermes-agent (cli)
- hermes (别名)
- hermes-acp (别名)
- hermes-agent (别名)

## 依赖

- certifi
- cryptography
- libyaml
- pillow
- pydantic
- python@3.14

## 构建依赖

- pkgconf
- rust

## 安装行为

- post-install 钩子: 未定义
- Bottle: 可用 于 arm64_linux, arm64_sequoia, arm64_sonoma, arm64_tahoe, sonoma, x86_64_linux

## 版本和新鲜度

- 页面生成时间: 2026-08-04
- 管理器版本: 2026.7.20
- 管理器更新时间: 2026-08-03
- 本地数据: OK
- 上游仓库: https://github.com/NousResearch/hermes-agent
- 检测到的最新版本: v2026.7.20 (当前)
## 项目历史与用法

Hermes Agent is Nous Research's open-source AI agent runtime, distributed as a CLI and companion desktop/messaging workflow. Its distinctive historical theme is not just tool use, but agent memory and self-improving skills stored across sessions.

### 项目历史

The GitHub repository was created on July 22, 2025. The README describes Hermes as a self-improving AI agent with a built-in learning loop that creates skills from experience, improves them during use, searches past conversations, and builds cross-session user context.

By 2026, the documentation and README described a broad runtime rather than a narrow terminal chatbot: a full TUI, model-provider switching, messaging gateways, scheduled automations, subagents, terminal backends, memory, MCP integrations, and research-oriented trajectory generation.

### 采用历史

Hermes Agent sits in the post-2024 generation of coding and task agents where the package is expected to install not only an executable, but also a managed runtime, provider configuration, skills, memory, and optional gateways. Its installer documentation says it handles Python, Node.js, ripgrep, ffmpeg, repository checkout, virtual environment, and global command setup.

The project's packaging story includes multiple command names in Homebrew and a managed install layout under `~/.hermes`, which reflects the way agent CLIs blurred the line between a local package and a persistent personal runtime.

### 使用方式

A user typically starts with `hermes`, chooses or configures a model provider, and then works through a terminal UI or messaging gateway. The README documents provider flexibility through Nous Portal, OpenRouter, OpenAI, user endpoints, and other backends.

Skills are central to day-to-day use. Official docs describe user and agent-created skills under `~/.hermes/skills/`, a bundled skills catalog, hub-installed skills, and a write-approval gate for users who want review before background self-improvement writes skill changes.

### 为什么软件包爱好者会关心

Hermes Agent is package-nerd interesting because it makes a local CLI behave like an extensible operating environment: it owns configuration, skills, memory, provider keys, optional messaging integrations, and tool execution backends. Installing the package is therefore closer to bootstrapping a development workstation than installing a single-purpose Unix command.

It also shows how AI-agent distributions began to depend on language-package managers and runtime bootstrapping. The installer leans on Python and Node ecosystems while exposing a single `hermes` command, making the package a wrapper around a larger managed environment.

### 时间线

- 2025-07-22: Public GitHub repository creation date recorded by GitHub.
- 2026: Documentation described installer-managed dependencies, managed checkout, virtual environment, and global `hermes` command setup.
- 2026: Official skills documentation described background self-improvement review and optional write approval for skill changes.

### Related projects

- Hermes Agent is related to autonomous coding and task agents such as Claude Code, Codex-style terminal agents, OpenClaw, and other tool-calling shells. The README explicitly documents migration from OpenClaw.
- Its skills model is related to agentskills.io and to the broader agent-memory pattern in which reusable procedures are stored outside the prompt and loaded only when relevant.

### 来源

- GitHub README for scope, install model, provider support, and migration notes.
- Official documentation home and installation page for product positioning and installer behavior.
- Official skills and skills-catalog pages for self-improvement and bundled skill behavior.


## 安全说明

没有找到 hermes-agent 的匹配本地密钥处理 manifest。软件包元数据仍在此发布，以便未来覆盖拥有稳定的软件包 URL。


## 源数据库详情

- **Source Database:** Homebrew formula API
- **Tap:** homebrew/core
- **Full Name:** hermes-agent
- **Version Scheme:** 0
- **Revision:** 0
- **Head Version:** HEAD
- **Bottle Stable Root URL:** <https://ghcr.io/v2/homebrew/core>
- **Deprecated:** no
- **Disabled:** no
- **Keg Only:** no
- **URL Keys:** head, stable

## 其他软件包管理器记录

- winget - fathah.HermesDesktop: normalized package name match | Windows Package Manager source index: fathah.HermesDesktop from https://cdn.winget.microsoft.com/cache/source.msix
- apk - hermes - 1.9-r10: installed executable or alias match | Alpine Linux edge package indexes: hermes from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz | Hermes is an anti-spam transparent SMTP proxy | https://hermes-project.com/
- apk - hermes-doc - 1.9-r10: installed executable or alias match | Alpine Linux edge package indexes: hermes-doc from https://dl-cdn.alpinelinux.org/alpine/edge/community/x86_64/APKINDEX.tar.gz | Hermes is an anti-spam transparent SMTP proxy (documentation) | https://hermes-project.com/
- dnf - Hermes - 1.3.3-55.fc45: installed executable or alias match | Fedora Rawhide package metadata: Hermes from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/210a2053c8e007daf9ae39c2a21daaed9b2ddd07d63ecffa597050361e73650c-primary.xml.zst | Pixel format conversion library | http://web.archive.org/web/20040202225109/http://www.clanlib.org/hermes/
- dnf - Hermes-devel - 1.3.3-55.fc45: installed executable or alias match | Fedora Rawhide package metadata: Hermes-devel from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/210a2053c8e007daf9ae39c2a21daaed9b2ddd07d63ecffa597050361e73650c-primary.xml.zst | Development libraries and header files for Hermes | http://web.archive.org/web/20040202225109/http://www.clanlib.org/hermes/


## 相关链接

- [MCP tool packages](https://pkg.so/zh-hans/mcp-tools/) - Mentions MCP or Model Context Protocol.
- [AI and agent packages](https://pkg.so/zh-hans/ai-agent-tools/) - Matched AI model, agent, coding-agent, orchestration, or MCP metadata.
- [Terminal utility packages](https://pkg.so/zh-hans/terminal-utilities/) - Matched terminal and command-line workflow metadata.
- [Networking and protocol packages](https://pkg.so/zh-hans/networking-protocol-tools/) - Matched network, protocol, or remote-service metadata.
- [python@3.14](https://pkg.so/zh-hans/brew/python-3-14/) - Runtime dependency declared by Homebrew.
- [pkgconf](https://pkg.so/zh-hans/brew/pkgconf/) - Build dependency declared by Homebrew.
- [rust](https://pkg.so/zh-hans/brew/rust/) - Build dependency declared by Homebrew.
- [block-goose-cli](https://pkg.so/zh-hans/brew/block-goose-cli/) - Shares pkgdb curated category or tags: agents, ai, ai-agent, cli.
- [openclaw-cli](https://pkg.so/zh-hans/brew/openclaw-cli/) - Shares pkgdb curated category or tags: agents, ai, automation, cli.
- [zeroclaw](https://pkg.so/zh-hans/brew/zeroclaw/) - Shares pkgdb curated category or tags: agents, ai, ai-agent, cli.
- [docker-agent](https://pkg.so/zh-hans/brew/docker-agent/) - Shares pkgdb curated category or tags: agents, ai, automation, cli.
- [ironclaw](https://pkg.so/zh-hans/brew/ironclaw/) - Shares pkgdb curated category or tags: agents, ai, automation, cli.
- [gptme](https://pkg.so/zh-hans/brew/gptme/) - Shares pkgdb curated category or tags: agents, ai, cli, llm.
- [zeptoclaw](https://pkg.so/zh-hans/brew/zeptoclaw/) - Shares pkgdb curated category or tags: agents, ai, ai-agent, cli.
- [librefang](https://pkg.so/zh-hans/brew/librefang/) - Shares pkgdb curated category or tags: agents, ai, automation, cli.
- [kimi-cli](https://pkg.so/zh-hans/brew/kimi-cli/) - Both packages touch the same language runtime or ecosystem. Shared terms: agent, agents, ai, ai-agent, certifi.
- [mistral-vibe](https://pkg.so/zh-hans/brew/mistral-vibe/) - Both packages touch the same language runtime or ecosystem. Shared terms: acp, agent, agents, ai, certifi.

## Combined YAML source

View the package source record on GitHub. [combined/hermes-agent.yml](https://github.com/mxcl/pkgdb/blob/main/combined/hermes-agent.yml)


## 来源

- pkg.so package database
- Geiger risk classifier
- package-page enrichment
- curated package history
- package version freshness
- pkgdb category and tag curation
- package relationship graph
- external package-manager database matches
- cross-ecosystem install command graph