NousResearch/hermes-agent (opens in a new tab)
Strong
Strong on every check. No grade is a guarantee, so only install what you need.
The agent that grows with you
What should I do?
It's widely used, looked after, open about itself, and shows none of the malware tricks we check for. Download it only from its official GitHub page, never from a copy, a file-sharing site or a link in a video.
Warning signs 2
Runs a script straight from the internet Good to know
The install step downloads and runs code in one line. Common with real tools too, but you can't see what runs.
Runs code during install Good to know
package.json runs "echo '✅ Node dependencies installed. Run: python run_agent.p" the moment you install it.
Talks to your AI 1
This repo has 1 file that AI coding tools like Claude Code, Cursor and Copilot read as instructions when you open the folder: AGENTS.md. We read them and found nothing that tries to take over your AI. It's still worth opening them yourself before you let an AI work in this folder.
Does it cost money?
We found no mention of paid plans or required accounts. Still check before you rely on it.
Why this grade?
It scored 92 out of 100. 85 or more is an A. Each area gets its own letter, and the overall grade can be at most one letter better than the weakest safety area ("Is it open about itself?" only costs points). Open a row to see what we checked.
Area grade ADo people trust it?, 30 out of 30 points
Good: Stars. 257,607 people starred it.
Stars are like bookmarks. Malware repos rarely have many real users, and lots of stars means lots of people have looked at it. Stars can be bought, so we also check how fast they came.
Good: Forks. 56,460 copies made by other developers.
A fork is a copy another developer made to build on. Real projects get copied; fake ones rarely do.
Good: Owner history. Organization created 3.4 years ago.
Scammers use brand-new accounts that get banned and replaced. An owner who has been around for years has more to lose.
Area grade AIs anyone looking after it?, 25 out of 25 points
Good: Recent updates. Last change 0 days ago.
Software nobody updates stops getting security fixes.
Good: Track record. Repo is 1.3 years old.
Older projects have had more time for problems to be spotted and reported.
Good: Releases. Publishes versioned releases.
A release is an official, finished version. Without one, you download whatever is in the code that day.
Area grade AIs it open about itself?, 15 out of 15 points
Good: License. Uses the MIT license.
A license says whether you're allowed to use it. Serious projects almost always have one.
Good: Instructions. Has a README that explains the project.
A README explains what the project does and how to use it. Malware often has a thin or copied one.
Good: Security contact. Tells people how to report security problems.
A security policy tells people how to report problems privately, so they get fixed before attackers use them.
Area grade BDoes it have good security habits?, 4 out of 5 points
So-so: Known security holes. 4 of the 1,220 parts it uses have a known security hole (for example zod@4.6.5, undici@6.29.0). Not every hole affects you, but the owner should update them.
Security holes that are public but not fixed yet are what attackers look for first. From OpenSSF Scorecard, or, when it has no data, from the project's list of parts (its lock file) looked up in OSV, Google's free public database of known security holes.
Area grade BAny malware tricks?, 23 out of 30 points
So-so: 2 warning signs. Each one is explained under Warning signs.
We look for tricks that keep showing up in malware: requests to turn off antivirus, locked zip files, cracks and free premium, hidden code, and AI instruction files that try to take over your assistant. Serious ones cap the grade, however popular the repo is.
Checked Oct 27, 2026. We re-check this repo every night. A grade is a set of warning signs, not a guarantee. How we score