Hermes Agent
Free personal agent that remembers your work and runs from the terminal or chat apps; sandbox it before real use.
Should you use it?
Pick it if
People comfortable with the command line who want an agent that learns their projects and answers from chat apps.
Best for: Command-line users who want a free agent that learns their projects (Automation and agents Top 20)
Skip it if
You want an assistant that is safe with no setup; a hosted app such as ChatGPT needs nothing installed.
You give up: Runs commands on your computer unless sandboxed; one flaw has no listed fix
The short version
- What this is
- A free, open-source AI agent from Nous Research that runs in your terminal or chat apps, remembers your projects and writes reusable skills as it works. You pick the model.
- Free under MIT; bring any model, hosted or your own s1 s3.
- Latest release v0.21.6 on 8 Oct 2026; first released in February s2 s4.
- Use the Docker backend and keep approvals on; the local backend has no isolation s5.
Good at
Weak at
Our take
Hermes Agent is a free agent you install on your own computer. It keeps notes on your projects, writes small reusable "skills" as it works, and can take requests from chat apps as well as the terminal s1 s3. You choose the model, so how well it does depends mostly on that choice s1.
The catch is access. With the local backend it runs commands straight on your computer, and its own docs say the safety rules are not a real sandbox s5. By default an extra model checks risky commands and denies them if you don't answer s5, which helps, but the docs still advise a Docker backend for serious use. Start there, with accounts you can afford to lose. Nous Research says Hermes has been cloned over 24 million times s2; no one outside has tested how well it does tasks, so we haven't scored it.
Not scored yet
This is a First look: the call above comes from the maker's own pages, so there is no score yet. When an independent agent benchmark from the last 90 days publishes results for Hermes Agent itself.
AgentsCoding
New to this? What the scores and labels mean
- 0 to 100
- Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
- Our verdict
- Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
- First look
- Just released. We say what it is and whether to bother, and give it a score once public results exist.
- No score yet
- None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
- Best buy
- Nothing cheaper scores as well for that job.
- Best free
- The best score for that job that costs nothing, through a free plan or by running on your own computer.
- Pay as you go
- No monthly plan: you pay for each use, usually through a developer account.
- Checked
- The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
- AI model
- The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
- Open source
- Free to download and run on your own computer, so nothing leaves your machine.
Alternatives
Better or cheaper for agents, from our scores, then the ones we'd also look at. The same kind of product comes first.
- ChatGPT (GPT-6)Top scoredApp70$20 a monthScores 70 in agents, first in our ranking; $20 a month. Side by side
- OpenClawAppFirst look: Worth tryingFreeThe other big free personal agent, with more chat apps supported. Side by side
- OpenAI Codex CLICoding agent70Coding$20 a monthFree open-source terminal agent focused on coding. Side by side
- OllamaPlatform80CodingFreeFree way to run local models, so prompts never leave your computer. Side by side
Evidence
Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.
How we scored this
Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.
No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score
Sources 5
- s1GitHub: NousResearch/hermes-agent
- s2The Next Web: Nous Research raises $90M to take its Hermes AI agent to businesses
- s3Hermes Agent website and Nous Portal pricing
- s4Hermes Agent releases on GitHub
- s5Hermes Agent docs: Security
Something here out of date or wrong? Report a mistake and we will check it against the source.
History 2 changes
Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.
- First look. No independent test of Hermes Agent itself, so not rated. Released date is the latest release; the catalog lists first release as 2026-02, exact day not confirmed.
- Nous Research raised $90M; The Next Web, citing the Wall Street Journal, reports a $1.5bn valuation.
Use it well 4 guides on this site
Pages on this site that help with the jobs above.