What actually differs between the three hosts?
The feature lists can sound similar. A practical comparison asks what installation involves, where project information is saved, which actions require approval and how usage is billed. Those details affect everyday work.
| Dimension | Hermes | OpenClaw | Claude Code |
|---|---|---|---|
| Install | One shell script; it provisions the runtimes | Official installer or a global npm package | Installer, Homebrew, WinGet, apt, dnf, apk, npm |
| Skill format | SKILL.md with a hermes metadata block | SKILL.md with an openclaw gating block | SKILL.md with optional invocation fields |
| Memory | Built-in store, searchable from the CLI | Plain Markdown: MEMORY.md, daily logs, USER.md | CLAUDE.md you write, auto memory it writes |
| Approval model | Prompts, then mined into allowlist proposals | Five exec modes plus revocable standing grants | Per-tool prompts, rules in a settings file |
| Cost | Open source; you pay the provider you route to | Open source; you pay the model key you bring | Needs a paid Claude plan or API billing |
| Platforms | macOS, Linux, WSL2; native Windows in beta | macOS, Linux, WSL2; native Windows unconfirmed | macOS, Windows, Ubuntu, Debian, Alpine |
| Best for | Recurring operations and scheduled jobs | An assistant in the channels you already use | Repository work with edits and tests |
Read the table one row at a time. Look for the requirements that matter to your team, such as an approval step before sending or a clear way to inspect saved information.
The install paths, side by side
Installation requirements differ. Record the product version and computer setup when testing, so a problem caused by missing software is not mistaken for a weakness in the agent.
# Hermes (macOS, Linux, WSL2)
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
# OpenClaw (Node 22.22.3+, 24.15+, or 25.9+)
npm install -g openclaw@latest --allow-scripts=openclaw
# Claude Code (macOS, Linux, WSL)
curl -fsSL https://claude.ai/install.sh | bash
# Claude Code (Windows PowerShell)
irm https://claude.ai/install.ps1 | iex- Time each install, then repeat it on a second machine
- Write down every prompt that asked for a key or a login
- Print the version string before you file a bug against anything
Where do skills and memory live?
~/.hermes/skills/<name>/SKILL.md Hermes, one root for everything
<workspace>/skills/<name>/SKILL.md OpenClaw, this agent only
~/.openclaw/skills/<name>/SKILL.md OpenClaw, installed with --global
~/.claude/skills/<name>/SKILL.md Claude Code, all your projects
.claude/skills/<name>/SKILL.md Claude Code, this repository onlySkills are the easy half. Every host reads a directory of folders, each holding a SKILL.md with YAML frontmatter, and each adds its own optional keys on top of the shared standard. Memory is the half that decides whether you can audit the agent six months later. Hermes keeps a built-in store you can search from the terminal. OpenClaw keeps plain Markdown: a curated MEMORY.md, dated daily logs, and a user profile file. Claude Code splits the job between the CLAUDE.md files you write and an auto memory directory it maintains for itself, which you can open and edit.
Approvals: the row that decides your risk
This is the row to read twice. OpenClaw exposes five exec modes, from deny through allowlist, ask, auto, and full, and keeps standing grants you can list and revoke. Claude Code prompts per tool call, keeps allow, ask, and deny rules in a settings file, and offers a plan mode that reads without writing. Hermes prompts, then lets you mine the approval history into allowlist proposals, which is the right shape once the same three commands keep coming back.
- Anything that can send mail or publish to a public channel
- Anything that can spend money or touch a payment method
- Anything that can delete files, records, or history
- Anything that can deploy code or rotate a credential
Which host should you run?
Choose a trial that reflects your work. For coding, check file editing, tests and change review. For recurring business tasks, check the needed application connections, scheduling and approvals. Confirm the current features in the product documentation before committing.
- Repository work and code review: Claude Code
- Recurring operations on a schedule: Hermes
- An assistant reachable from your chat channels: OpenClaw
Run one acceptance test before you commit
Use the same harmless task for each candidate, such as turning fictional meeting notes into a saved summary. Compare setup time, output quality, approval clarity and how easily you can stop the run. Repeat it to see whether the process is dependable.
hermes skills list # what Hermes will load this session
openclaw approvals get # the effective exec policy
claude doctor # install health and settings errorsCan the same SKILL.md run on all three hosts?
The main procedure may transfer, but product-specific settings, tools and install locations can differ. Test it in each application before relying on it for a client task.
Which host is safest for a team that is not technical?
Choose a product your team can configure and review confidently. Test its approval prompts, access limits and stop controls on sample work before using sensitive information.
Do we have to standardize on just one?
No, but each additional application adds settings and permissions to maintain. Start with the one that fits your first task and add another only for a clear need.
Choose the host for your first workflow
Compare the hosts against the job and the review process your team needs. We can discuss your current tools and help identify a small first test before you commit to a wider setup.