Hermes Agent vs NanoClaw
How the two compare on price, platforms, what they can act on and how they ask before acting. Facts come from each agent's sources page.
| Hermes Agent | NanoClaw | |
|---|---|---|
| Maker | Nous Research | NanoCo |
| Cheapest paid plan | Free | Free |
| Free tier | Yes: the agent is free and open source under the MIT license; the site states model providers and optional hosted services such as Nous Portal have their own pricing | Yes: free and open source under the MIT license; model provider usage may cost money |
| Platforms | macOSWindowsLinuxSelf hostedCloud (Nous Portal)CLITelegramDiscordSlackWhatsAppSignalEmail | macOSLinuxWindows (WSL2)Self hostedWhatsAppTelegramDiscordSlackMicrosoft TeamsMattermostiMessageSignalMatrixGoogle ChatWebexEmail |
| Can act on | BrowserFilesCodeMessagesEmailWeb searchImages | MessagesEmailBrowserFilesCode |
| Approval model | Dangerous shell commands require approval. The default smart mode uses an auxiliary model to auto approve low risk commands, auto deny clearly dangerous ones and ask the user in uncertain cases; manual mode always asks and off (YOLO) disables prompts. Cron, single query and unattended sessions deny dangerous commands by default, a hardline blocklist can never be overridden, and checks are skipped inside container backends. | Agents run in isolated containers and never see real credentials; an OneCLI credential gateway checks user defined policies and pauses sensitive outbound requests until the user approves them through a native card in the chat app. The FAQ also lists egress lockdown, mount rules and sender policies. |
| Launched | Feb 25, 2026 | Jan 31, 2026 |
| Last update | Oct 15, 2026: Hermes Agent v0.22.2 | Oct 9, 2026: NanoClaw 2026.10.0 |
See sources on the Hermes Agent and NanoClaw pages.
Track both every week