ANOLISA is a server-side operating layer for AI agent workloads that provides terminal access, token-saving tool-output compression, runtime controls, security, observability, skills, memory, and sandbox management. It is for running and supervising agents from a Linux terminal while retaining an existing shell, agent framework, and sandbox. The catalogue add-ons are components of its agent operating environment and workflows.
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 agentmods add skills/alibaba/anolisa/install-hermesnpx skills add alibaba/anolisa --skill install-hermesgit clone --depth 1 https://github.com/alibaba/anolisaWrote 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/alibaba/anolisa/install-hermes)<a href="https://agentmods.dev/skills/alibaba/anolisa/install-hermes"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/install-hermes.svg" alt="Measured on agentmods" 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 | $0.00124 | $0.04695 |
| Opus 5 | $0.00062 | $0.02348 |
| Sonnet 5 | $0.00025 | $0.00939 |
| Haiku 4.5 | $0.00012 | $0.00470 |
Grade C, and why
install-hermes 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.hermes/hermes-agent/node_modules Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://127.0.0.1:8642/health # gateway 健康 How it starts
The opening of the file, as written. The whole thing — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Agent 一键安装与配置
操作系统: Linux / macOS / WSL2 / Android(Termux)。不支持原生 Windows。
意图识别与行动映射
当用户表达以下意图时，按对应工作流执行：
| 用户说 | 对应工作流 |
|---|---|
| "安装 Hermes" / "从零开始" | 工作流 1: 全新安装 |
| "安装 [Provider 名]" / "配置 [模型名]" / "接入 [供应商]" | 工作流 2: 添加 Provider |
| "接入 [平台名]" / "配置 [Telegram/钉钉/飞书/微信]" / "安装 Bot" | 工作流 3: 添加消息平台 |
| "安装 Workspace" / "Web UI" / "可视化界面" | 工作流 4: 安装 Hermes Workspace |
| "从 OpenClaw 迁移" | 工作流 5: OpenClaw 迁移 |
| "检查配置" / "出问题" / "不能用" | 工作流 6: 诊断与修复 |
工作流 1: 全新安装
前提检查
git --version # 必须可用
执行安装
bash ./scripts/install.sh
source ~/.bashrc # 或 source ~/.zshrc
hermes doctor # 验证
安装过程说明：
- 脚本默认最小安装（跳过 daytona/playwright/WhatsApp 等重型组件），安装速度快
- 需要完整功能（浏览器工具、WhatsApp 等）时加
--full参数- 脚本默认跳过交互式配置向导，安装完后运行
hermes setup再配置- 如需安装时直接配置，加
--with-setup参数- CI/自动化场景直接运行即可，不会出现任何交互阻塞
- 安装完成后会自动安装 tokenless 插件（token 用量追踪和响应压缩），无需额外操作
安装参数说明：
| 参数 | 说明 |
|---|---|
| （无参数） | 最小安装，仅核心包，速度最快（推荐新手） |
--full |
安装所有 extras（daytona、playwright、WhatsApp 等） |
--with-setup |
安装完后启动配置向导 |
--skip-tokenless |
跳过 tokenless 插件自动安装 |
首次配置
hermes model # 选择 Provider 和模型
hermes # 启动首次对话验证
工作流 2: 添加 Provider
用户意图："我要安装 OpenRouter"、"接入 DeepSeek"、"用 Claude"、"配置 Kimi" 等。
Step 1: 确定 Provider 类型
从以下速查表识别用户指定的 Provider：
| Provider | 环境变量名 | 交互式命令 | 详细配置参考 |
|---|---|---|---|
| Alibaba / 通义千问 | DASHSCOPE_API_KEY |
hermes model |
model.md |
| DeepSeek | DEEPSEEK_API_KEY |
hermes model |
model.md |
| z.ai / 智谱 GLM | GLM_API_KEY |
hermes model |
model.md |
| Kimi / Moonshot 中国版 | KIMI_CN_API_KEY |
hermes model |
model.md |
| MiniMax 中国 | MINIMAX_CN_API_KEY |
hermes model |
model.md |
| Ollama (本地) | 无需密钥 | hermes model |
model.md |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 442 lines · 124 tokens per session scan C 250c268d790e
install-hermes is a skill published in the GitHub repository alibaba/anolisa (618 stars, last pushed yesterday), licensed Apache-2.0. It adds 124 tokens to every session and 4,695 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, 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
beevibe-team-mesh-negotiation
Multi-round negotiation protocol — covers both initiator and peer roles. Use when about to call negotiate(), when receiving a intent block as a peer, or when receiving an 'escalated' sentinel from a blocked respondnegotiate. Covers proposal crafting, counter-strategy, deadlock detection, when to accept early…
beevibe-verify-pr
CI verification before marking a PR-bearing task done. Use BEFORE calling mcpbeevibeupdateprogress(done) on any session whose deliverable is a pull request — including the first dispatch (you opened the PR with gh pr create) and any revision dispatch (you pushed new commits to an existing PR). Watches the PR's…
beevibe-pre-task-setup
Cold-start git workspace setup for a fresh beevibe task. Use at the start of a session whose intent has a block but NO or block — i.e. the first dispatch of this task. Checks for an existing repo clone, pulls the base branch if present (clone if missing), prunes any per-task worktrees from earlier tasks whose work has…
beevibe-use-repo
You are the child agent inside a fresh Docker sandbox. Borrow the given GitHub repo, produce a real artifact for the goal, and export it. Do not review the repo. The proof is that it works.
beevibe-discover-repo
Find the best GitHub repo for a goal, then call userepo to run it in a sandbox. Use whenever the user's goal requires a capability you don't have natively and you haven't been given a specific repo.
spec-converge
Iteratively review an instar-development spec with multi-angle internal reviewers (security, scalability, adversarial, integration, decision-completeness, lessons-aware) and real cross-model external reviewers routed through the agent's own installed CLIs (codex → GPT-tier, gemini → Gemini-tier; one pass per available…