agentos.guide › blog

Hermes Agent Browser: What It Is, The Quick-Start And Where It Fits In An Agent OS

By Julian Goldie · 12 October 2026 · agentos.guide

Hermes Agent browser is the built-in browser automation toolset that lets Hermes Agent open a real web page, read it, click, type and take screenshots for you.

It ships inside Hermes Agent, the free open-source agent from Nous Research, so there is nothing extra to buy.

This guide gives you the ten-minute quick-start first, then every backend, how logins work, the limits and where the browser sits inside an Agent OS.

Hermes Agent browser at a glance

Every fact in that table comes from the official Hermes browser docs, which I re-read on 12 October 2026.

What the Hermes Agent browser is

Hermes Agent is the free, open-source AI agent from Nous Research.

The browser toolset is the part of it that drives a real web browser.

The docs describe it as a full browser automation toolset with multiple backend options.

The agent doesn't look at pixels by default.

Hermes turns each page into an accessibility tree, which is a text snapshot of the page.

Each button, link and field in that snapshot gets a reference such as @e1 or @e5.

The model reads the snapshot, picks a reference and calls a tool to click it or type into it.

When a page needs a visual check, the model can ask for a screenshot and a vision analysis.

Quick-start: get the Hermes Agent browser working in ten minutes

This is the shortest honest route from a fresh install to a first click.

I checked every command against the help output of my own install, which is Hermes version 0.21.4.

When I ran the list command on 12 October 2026, the browser toolset already showed as enabled for the terminal.

The toolsets reference says the default terminal toolset includes the browser, so the first two steps are usually a check.

You can switch it off at any time with hermes tools disable browser, or with /tools disable browser inside a chat.

What the browser toolset can do

The docs list these built-in tools.

The toolsets reference also lists a set of vault tools that fill saved logins into sign-in pages.

There is one more tool called browser_exec.

The docs say Browser Use mode is now the default, so when the browser-use command-line tool can run, the model gets that single tool and writes short Python to drive the page.

If it can't run, Hermes falls back to the built-in tools in the table.

The docs only offer that tool to sessions that also have terminal access, because it runs model-written code on your machine.

You can force the built-in tools by typing /browser use off.

I cover that project in my Hermes Agent browser use guide, so this page stays on the toolset.

🔥 Want the exact the Hermes browser toolset setup I run inside my Agent OS?

Inside the AI Profit Boardroom you get the installable Agent OS, step-by-step video tutorials, four coaching calls a week and 3,400+ members building real automations.

→ Get access here

Browser tools vs web search and extract

These two toolsets do different jobs, and mixing them up costs you tokens.

The toolsets reference adds that web search is deliberately not part of the browser toolset.

That means you can disable the browser and your agent can still look things up.

The browser backends the docs list

A backend is simply where the browser runs.

You choose one in the Browser Automation section of the tools menu.

The docs point out that a provider key only supplies credentials, and the active provider is the one you selected in that menu.

Plain local browsing uses the packaged Chromium, so your installed Chrome is never touched.

The docs also describe hybrid routing, where a cloud browser handles public sites and a local sidecar handles localhost and LAN addresses.

I rank these options in my best browser for Hermes list, so I won't pick a winner here.

Logged-in sessions, cookies and passwords

The default local browser is a clean throwaway profile, so the agent is logged into nothing.

The docs give you two main ways to change that on your own machine.

Real profile browsing is the setting browser.use_real_profile, and it is off by default.

When it is on, Hermes copies your active browser profile into a managed snapshot and launches your real browser on that copy.

The docs say your live profile is never opened directly, and the snapshot is deleted after you turn the setting off.

It supports Chrome, Edge, Brave and Chromium, and it stops with a clear message if your default browser is Firefox.

You should quit your browser before starting a real-profile session, because a running browser usually locks the login databases.

The credential vault is the second route.

The first time the agent reaches a sign-in page with no saved login, it asks you in a masked prompt.

The docs say the password is encrypted on your machine and filled into the page without the model seeing it.

The vault can also enter two-factor codes when you save the authenticator key with the login.

Approvals and safety

The docs call real profile browsing a consent-gated convenience and not an isolation boundary.

A page the agent visits in that mode runs with your real logins, so I'd only enable it for a job that needs it.

• A saved password is only filled when the page origin exactly matches the saved origin.
• The website blocklist blocks listed domains across web search, web extract and browser navigation.
• Private and internal addresses are blocked on cloud backends and handled by a local browser instead.
• The browser.restrict_evaluate setting adds a denylist over sensitive JavaScript such as cookies and storage.
• Hermes never closes your browser to free a locked profile without asking you first.

The docs are also honest that once a password is typed into a site, that site has it.

🔥 Want the exact the Hermes browser toolset setup I run inside my Agent OS?

Inside the AI Profit Boardroom you get the installable Agent OS, step-by-step video tutorials, four coaching calls a week and 3,400+ members building real automations.

→ Get access here

How the Hermes Agent browser fits inside an Agent OS

An Agent OS is one dashboard where your agents, memory and tools live together.

In mine, Hermes is one of the agents behind that dashboard, and the browser toolset is one of the tools it carries into every room.

The pattern I'd copy is a ladder.

The agent tries web search first, web extract second and the browser third.

That keeps cheap lookups cheap and saves the browser for pages that need it.

The full tour of the dashboard is in the Hermes Command Desk guide.

A real example from my own setup

I use a Hermes skill for a daily AI news scan, and I published it in my Hermes AI skills guide.

That skill follows the ladder above.

If web search and web extract both come back empty, it calls browser_navigate and then browser_snapshot with the full option on.

My note in that skill says the web tools returned nothing in March 2026 and the browser returned the full pages every time.

It also uses browser_scroll to reveal more of a long article.

The same skill records that Product Hunt showed a bot check, and my instruction to the agent was to skip that site.

The browser toolset is not Computer Use

The video at the top of this page covers Hermes Computer Use, which is a neighbouring feature.

Computer Use controls desktop apps in the background, and I walk through it in the Hermes Takeover Engine guide.

The Hermes docs say browser work, including pages in a signed-in profile, goes through the browser toolset and not through Computer Use.

My rule is simple.

I use the browser toolset for websites and Computer Use for native apps.

Costs

Hermes Agent and the browser toolset are free.

Local browsing and the connect command cost nothing beyond your model tokens.

The docs say cloud sessions consume provider credits, so Browser Use, Browserbase and Firecrawl charge on their own plans.

The Tool Gateway route needs a paid Nous Portal subscription.

I haven't quoted provider prices, because they change and their own pages are the right source.

Limits, CAPTCHAs and bot detection

The docs list the limits plainly.

• The browser works from the text snapshot and not from pixel coordinates.
• A snapshot over 15,000 characters is truncated, and the full version is saved to a file the agent can read.
• The browser cannot download files.
• Cloud sessions expire based on your provider's plan.
• Idle sessions close after 120 seconds by default.
• Lightpanda has no graphical renderer, so screenshots aren't available on that engine in the default mode.

The docs say Browser Use cloud includes CAPTCHA solving, and Browserbase lists it under basic stealth.

Headed mode keeps a visible window open so you can solve a challenge by hand.

Nothing in the docs promises that every site will accept an automated visitor.

Troubleshooting

The /browser status command shows what the browser is connected to, which is the first thing I'd check.

FAQ

What is the Hermes Agent browser?

The Hermes Agent browser is the browser automation toolset built into Hermes Agent from Nous Research. It lets the agent open pages, read them as text snapshots, click, type, scroll and take screenshots.

How do I enable the browser in Hermes Agent?

Run hermes tools list to check it, then run hermes tools enable browser if it shows as disabled. Run hermes tools and open Browser Automation to choose where the browser runs.

How is the Hermes browser different from web search?

Web search and web extract fetch information, and the docs say they are faster and cheaper for simple retrieval. The browser toolset drives a live page, so it is for clicking, typing and dynamic content.

Can Hermes Agent use my logged-in browser?

Yes. Real profile browsing drives a copy of your active Chrome, Edge, Brave or Chromium profile, and the credential vault can fill saved logins. Real profile browsing is off by default.

Is the Hermes Agent browser free?

The toolset is free and local browsing costs only your model tokens. Cloud browser providers charge on their own plans, and the Tool Gateway needs a paid Nous Portal subscription.

Is the Hermes browser the same as Hermes Computer Use?

No. Computer Use controls desktop apps, and the Hermes docs say browser work goes through the browser toolset instead.

Final word on the Hermes Agent browser

Check the toolset, start on the free local browser and keep real logins off until one job needs them.

Use web search for lookups and save the clicks for the Hermes Agent browser.

Related guides on agentos.guide

→ These 10 Hermes AI Skills Run My Business

→ The Hermes Takeover Engine

→ The Hermes Command Desk

→ The Best Hermes Agent Tools

📺 Video notes + links to the tools 👉

🎥 Learn how I make these videos 👉

🆓 Get a FREE AI Course + Community + 1,000 AI Agents 👉

← all guides on agentos.guide