Skip to content

Hermes Agent vs NanoClaw

Price, platforms and features side by side. The table says where each price was read and when.

Hermes Agent

Open-source AI agent with persistent memory and a messaging gateway

Free plan · from $20/mo

NanoClaw

Open-source personal AI agent that runs in containers you host

Free

Where they differ

  • Hermes Agent starts at $20 per month for the optional Nous Portal Plus tier; the agent is free. NanoClaw is free.
  • Only Hermes Agent lists a web app.
  • NanoClaw also covers templates.
In commonFree planmacOSWindowsLinuxOpen sourceSelf-hostableChat assistantWorkflow automationAI agents

At a glance

Hermes AgentNanoClaw
PricingFree planFree
Starts at$20 per month for the optional Nous Portal Plus tier; the agent is freeFree
Free planHermes Agent is free and open source under the MIT license. You connect your own model provider, or a free Nous Portal account that is limited to free models.The whole product is free and open source under the MIT license. You supply the computer it runs on and your own AI provider account, which the provider bills separately.
Free trialNone listedNone listed
Web
macOS
Windows
Linux
Made byNous Research, Inc.NanoCo
Price read fromhermes-agent.nousresearch.comnanoclaw.dev
CheckedOct 5, 2026Oct 6, 2026

Who each one suits

Hermes Agent

  • Developers who want an agent on their own machine, server or VPS
  • Reaching one agent from Telegram, Discord, Slack or WhatsApp
  • Unattended scheduled jobs such as reports and briefings

NanoClaw

  • People who want a personal agent running on hardware they control
  • Developers who want a small codebase they can read and fork
  • Giving an agent shell access inside a container instead of on the host

Worth knowing

Hermes Agent

  • The agent is free, but paid models cost extra: your own provider's rates, or Nous Portal tiers from $20 a month.
  • Desktop apps are offered for macOS and Windows; on Linux the install is through the terminal.
  • The platform support page lists no iOS version, and Android runs only through a prerelease Termux package.
  • Hermes Cloud needs $2 of Nous credit or an active subscription to deploy, and bills inference separately from the instance.

NanoClaw

  • There is no hosted version: you install it yourself with git and a terminal, and the computer must stay on for the agent to respond.
  • The software is free, but hosted model usage is billed by the provider you connect, through a subscription or an API key.
  • Docker is the only supported container runtime, and Windows is supported only through WSL2.
  • The site lists no graphical app of its own: you talk to it in the terminal or through the messaging channels you connect.

Key features

Hermes Agent

Messaging gateway
One gateway connects the agent to Telegram, Discord, Slack, WhatsApp, Signal, Matrix, email, Microsoft Teams and other platforms, more than 20 in all, sharing a single memory.
Memory and self-written skills
The agent keeps memory across sessions, creates reusable skills from work it has done and revises them in use. Skills follow the open agentskills.io format.
Scheduled automations
Built-in cron accepts natural-language schedules for reports, backups and briefings and delivers the results to any connected platform.
Subagents
Isolated subagents with their own conversations and terminals handle parallel workstreams without filling the main agent's context.
Terminal backends and sandboxing
Commands run locally or in Docker, over SSH, or on Daytona, Singularity, Modal or Vercel Sandbox, with command approval and container isolation.
Nous Portal and Hermes Cloud
A Portal subscription supplies credits for 200+ models and hosted web search, image generation, text-to-speech and browser tools. Hermes Cloud hosts an always-on agent, billed daily.

NanoClaw

Messaging channels
Talk to agents in the terminal or connect WhatsApp, Telegram, Slack, Discord, Signal, iMessage, Microsoft Teams and other channels, each installed on demand with an /add- skill.
Container isolation
Every active session runs in its own unprivileged Docker container and sees only the files you mount, so shell commands run inside the container rather than on your host.
Credential vault
By default agents never hold raw API keys: outbound requests pass through OneCLI's Agent Vault, which injects credentials at request time and applies per-agent policies and rate limits.
Scheduled tasks
Ask an agent in chat for a reminder or a recurring job and it creates a task on a cron-style schedule. Tasks can also be listed, paused and cancelled with the ncl admin CLI.
Choice of model provider
Claude is the default, Codex can be chosen during setup, and OpenCode or local Ollama models can be added later. Each agent group can use a different provider.
Templates and skills
A template stamps out a prebuilt agent with a persona, skills, MCP servers and paused recurring tasks, while skills add channels, providers or tools to your own fork.

Plans

Hermes Agent

  • Hermes Agent$0

    The complete MIT-licensed agent, run on your own machine or server with a model provider of your choice.

  • Nous Portal Free$0

    Free models only, standard rate limits and no monthly credits.

  • Nous Portal Plus$20

    per month

    $22 of monthly credits (a 10% bonus) with a $10 rollover cap, 200+ models, hosted tool usage and high rate limits.

  • Nous Portal Super$100

    per month

    $110 of monthly credits with a $50 rollover cap, plus the same models, hosted tools and rate limits as Plus.

  • Nous Portal Ultra$200

    per month

    $220 of monthly credits with a $100 rollover cap, plus the same models, hosted tools and rate limits as Plus.

  • Hermes CloudFrom $0.56

    per day while running, billed from Nous credit

    Optional always-on hosting: Medium is $0.56 a day and Large $1.09 while running, $0.03 a day stopped. Inference and tool usage are billed separately.

NanoClaw

  • NanoClaw (MIT licensed)Free

    The complete self-hosted agent, with channels, providers and tools added as skills. Model usage is billed by the provider you connect, unless you run local Ollama models.

More comparisons