English

Hermes Agent Alternatives: 5 Open-Source Agents to Run Instead

Five open-source alternatives to Hermes Agent, ranked for self-hosters: who sandboxes commands, who ships phone apps, and who keeps setup small.

At a glance

At a glance
BotLicenseChat apps
Hermes AgentMIT261.7KYesNoTelegram, WhatsApp, iMessage, Discord, SlackFrom $20/mo
ZeroClawMIT OR Apache-2.033.3KYesYesTelegram, WhatsApp, DiscordFree
OpenClawMIT394.2KYesNoTelegram, WhatsApp, iMessage, Discord, SlackFree
NanoClawMIT31.1KYesYesTelegram, WhatsApp, iMessage, Discord, SlackFree
RakazoApache-2.07.5KYesYesTelegram, WhatsApp, iMessage, SlackFrom $10/mo
NemoClawApache-2.023KYesYesTelegram, Discord, SlackFree
GitHub stars as of Nov 8, 2026

Checklist

Checklist
Hermes AgentZeroClawOpenClawNanoClawRakazoNemoClaw
Open-source licenseYesYesYesYesYesYes
Runs local modelsYesYesYesYesYesYes
Sandboxed by defaultNoYesNoYesYesYes
No telemetry by defaultYesYesNoNoYesNo
Lives in your chat appsYesYesYesYesYesYes
Works while you're awayYesYesYesYesYesYes

Hermes Agent from Nous Research gets a lot right for a self-hoster: MIT license, no shared metrics unless you opt in, local models, 20+ chat platforms and an agent that writes its own reusable skills. If you’re reading this, one of its gaps probably got in the way. New to it? Start with what Hermes Agent is.

Where Hermes Agent falls short

Commands run on your machine. The terminal backend defaults to local, and container isolation is an optional setting. An agent that learns new skills and reads your messages is exactly the kind you’d want boxed in.

No phone app. On Android it’s a command-line install through Termux, and there’s nothing native for iOS. You reach it through a chat app or not at all.

Setup assumes a server admin. It expects comfort with the command line and with running your own server. There’s no Linux desktop package, and iMessage needs a separate BlueBubbles server on a Mac.

Paid extras. Hosted web search, image generation and speech need a Nous Portal plan or your own API keys.

We ranked the alternatives mostly on the first point, since it’s the one that can cost you data, then on how much setup they take.

1. ZeroClaw: sandboxed by default, one binary

ZeroClaw is the strongest pick if isolation is why you’re leaving. Its recommended Balanced profile asks before medium-risk actions, blocks high-risk ones, limits file access to the workspace and runs tools in an OS sandbox (Seatbelt on macOS, Firejail on Linux). It’s a single Rust binary configured with one TOML file, sends no telemetry, and runs local models through Ollama with fallback chains between providers.

Hermes users will miss two things: the self-improving skills loop, and channel breadth in the standard build. Slack, iMessage and Signal need a source build with extra features.

ZeroClaw homepage headline: The personal AI agent you actually own, one lightweight Rust binary on your machine with your keys or your local models
ZeroClaw's homepagezeroclaw.com

2. OpenClaw: apps everywhere, biggest community

OpenClaw is the agent Hermes imports from, and it’s the answer to the phone-app gap: it has apps for macOS, Windows, Linux, iOS and Android, 29 chat channels and 142 official plugins. Its desktop apps also cover Linux, where Hermes has no desktop package.

It does nothing for the sandbox problem. Sandboxing is off by default, and it sends a daily update check with version and system details until you set update.checkOnStart: false. Our Hermes vs OpenClaw comparison goes deeper.

WhatsApp chat with an OpenClaw assistant giving casual travel advice to a user in Marrakech
Chatting with OpenClaw in WhatsAppdocs.openclaw.ai

3. NanoClaw: one container per agent

NanoClaw runs every agent in its own Docker container that sees only the folders you mount, and routes outbound calls through a credential gateway so agents never hold raw keys. Like Hermes profiles, you can run several separate agents, each with its own memory and access.

It’s tied to Claude and Claude Code: you customize it by having Claude Code edit your fork, with no config files. It also sends anonymous setup diagnostics unless you set NANOCLAW_NO_DIAGNOSTICS=1, and needs WSL2 on Windows.

NanoClaw setup wizard in a terminal explaining that the assistant lives in its own sandbox and asking whether to fetch a hardened image or build it locally
NanoClaw's setup wizard choosing the agent's sandbox imagedocs.nanoclaw.dev

4. Rakazo: sandboxed bots with mobile apps

Rakazo, which we make, covers the two gaps together: each bot gets its own sandboxed computer with browser, terminal and desktop, and there are iOS and Android apps as well as desktop ones. It’s Apache-2.0, sends no product analytics when self-hosted, and works with local models through Ollama or LM Studio or with a Claude or ChatGPT subscription.

It’s still in beta, needs Docker Engine with Compose, and Telegram, WhatsApp and iMessage only work on a self-hosted install.

Rakazo web app with a chat with a bot called Chief and a side panel showing the bot's live browser screen, a Take control button and routines
A Rakazo bot chat with its computer screen beside itgithub.com

5. NemoClaw: keep Hermes, put it in a sandbox

NemoClaw isn’t really a replacement. It’s NVIDIA’s stack for running OpenClaw, Hermes Agent or LangChain Deep Agents Code inside an OpenShell sandbox, with network destinations blocked until an operator approves them and credentials kept outside the sandbox. If you like Hermes and only object to it running loose, this lets you keep it.

The cost is weight and maturity: 8 GB RAM minimum, a 2.4 GB sandbox image, alpha status, and telemetry to NVIDIA unless you set NEMOCLAW_DISABLE_TELEMETRY=1. What NemoClaw is explains the setup.

NemoClaw high-level component diagram: users and operators, NemoClaw control (CLI, installer, dashboard), the OpenShell gateway, the sandbox running OpenClaw, inference, integrations and state
How NemoClaw wraps an agent in an OpenShell sandboxgithub.com

Which one to pick

  • Leaving because commands aren’t sandboxed: ZeroClaw, or NanoClaw if you already work in Claude Code.
  • Leaving because there’s no phone app: OpenClaw, or Rakazo if you also want sandboxing.
  • Happy with Hermes but want isolation and have the hardware: NemoClaw.

The full field, beyond Hermes-shaped agents, is in our list of the best open-source AI agents.

Alternatives

  1. ZeroClaw

    Free

    Personal AI agent in one Rust binary, MIT or Apache-2.0, with local or cloud models, 30+ channels, approval gates and an OS sandbox on by default.

    Meets every check: one Rust binary, approval gates and an OS sandbox on by default, no telemetry, local models.

    Strengths

    • Safe defaults: the recommended profile asks before medium-risk actions, blocks high-risk ones, keeps files in the workspace and runs tools in an OS sandbox
    • One small Rust binary with one config file, running on macOS, Linux, Windows and boards like a Raspberry Pi
    • More than 30 channels, plus a web dashboard for chat, memory, config and cron
    • Provider fallback chains, local models through Ollama, and cryptographic receipts for tool calls
    • States plainly that it sends no telemetry and needs no cloud account or license server

    Weaknesses

    • Slack, iMessage, Signal and several other channels are not in the standard release; you build from source with extra features to get them
    • `zeroclaw quickstart` only sets up the model provider; channels and risk profiles mean editing the TOML config file
    • The Docker sandbox backend isn't picked automatically under the default native runtime
    • Model costs are on you
    Visit ZeroClaw

  2. OpenClaw

    Free

    Free, MIT-licensed personal AI agent that runs on your own computer and takes orders from WhatsApp, Telegram, iMessage, Slack and 20+ other chat apps.

    The biggest ecosystem and every chat app, but sandboxing is off and telemetry is on by default.

    Strengths

    • Free and MIT licensed, with no paid tier
    • Runs on your own hardware, and state, memory and credentials stay there
    • Works in 29 chat channels, including WhatsApp, Telegram, iMessage, Slack, Discord and Microsoft Teams
    • Model-agnostic: 64 model and media providers, plus local models
    • Large ecosystem of skills and 142 official plugins, and very active development

    Weaknesses

    • Model costs are on you and can run high: testers and users have reported spending over $100 in a day with expensive models
    • Sandboxing is off by default and the agent can run commands on the host unless you turn on approvals
    • Setup and upkeep expect comfort with the command line; maintainers warn it is risky for non-technical users
    • Broad access to email, messages and the system makes prompt injection and malicious third-party skills a real risk
    Visit OpenClaw

  3. NanoClaw

    Free

    Small, MIT-licensed OpenClaw alternative that runs each agent in its own Docker container and chats with you on WhatsApp, Telegram, Slack, Discord and more.

    Every agent in its own container and a tiny codebase, but tied to Claude Code and sends setup diagnostics by default.

    Strengths

    • Every agent runs in its own Docker container and sees only the folders you mount, so shell access stays off your host
    • Small codebase (one host process and a handful of files) that you customize by having Claude Code edit your fork
    • Agents never hold raw API keys: outbound calls go through a credential gateway with per-agent policies and rate limits
    • Many chat channels, including WhatsApp, Telegram, Slack, Discord, iMessage, Teams, Matrix and email, with one or several agents per channel
    • Scheduled tasks with optional script gates that skip waking the agent when there's nothing to do

    Weaknesses

    • Built around Claude and Claude Code: customizing, debugging and adding channels all go through Claude Code
    • Sends anonymous setup diagnostics unless you set NANOCLAW_NO_DIAGNOSTICS=1
    • No config files by design, so every change means editing code in your own fork
    • Needs Docker, and Windows only works through WSL2
    Visit NanoClaw

  4. Rakazo

    From $10/mo

    Open-source, self-hostable platform for persistent AI bots that each get a job, a computer, memory and routines, using the model you choose.

    Our own product. Meets every check: Apache-2.0, sandboxed bot computers, no telemetry by default, any model you connect.

    Strengths

    • Open source (Apache-2.0) and fully self-hostable, including with local models
    • Choice of model per bot, including existing Claude or ChatGPT subscriptions
    • Bots keep working on schedules and triggers with their own cloud computer
    • Approval controls over which actions a bot may take on its own

    Weaknesses

    • Still in beta, with frequent releases
    • You supply and pay for the model on the hosted plans, unless you buy Rakazo credits
    • Telegram, WhatsApp and iMessage/SMS are only available when self-hosted
    • More setup than a single chat app
    Visit Rakazo

  5. NemoClaw

    Free

    NVIDIA's Apache-2.0 stack for running OpenClaw, Hermes or Deep Agents inside locked-down OpenShell sandboxes with managed inference. Alpha.

    Puts OpenClaw or Hermes in a locked-down sandbox, but it's alpha, heavy to run and sends telemetry by default.

    Strengths

    • Puts OpenClaw or Hermes Agent in a sandbox with network, filesystem and process controls instead of running it on your host
    • Unapproved network destinations are blocked and surfaced for an operator to approve
    • Inference, messaging and MCP credentials stay outside the sandbox
    • Backed by NVIDIA, with local inference through Ollama, vLLM or NIM and a tested path on DGX Spark

    Weaknesses

    • Alpha: maintainers support it on a best-effort basis, and several channels are experimental
    • A wrapper, not an agent: what the bot can do depends on the OpenClaw or Hermes version inside
    • Heavier than running the agent alone: 8 GB RAM minimum, a 2.4 GB sandbox image and a container runtime
    • The CLI sends operation telemetry to NVIDIA unless you set NEMOCLAW_DISABLE_TELEMETRY=1
    Visit NemoClaw

Features

Features
Hermes AgentZeroClawOpenClawNanoClawRakazoNemoClaw
Web searchYesYesYesYesYesYes
Image generationYesYesYesUnknownYesUnknown
Voice modeYesYesYesUnknownYesUnknown
File uploadsYesYesYesYesYesUnknown
MemoryYesYesYesYesYesUnknown
Takes actions for youYesYesYesYesYesYes
App integrationsYesYesYesYesYesYes
Works on its ownYesYesYesYesYesYes
Messages you firstYesYesYesYesYesUnknown
Runs several botsYesYesYesYesYesUnknown

Sources

Hermes Agent

  1. NousResearch/hermes-agent on GitHub (MIT, v0.23.0)
  2. Hermes Agent homepage and Nous Portal pricing
  3. Hermes Agent documentation
  4. Hermes Agent docs: Profiles, running multiple agents
  5. Hermes Agent docs: Bot Mode
  6. Hermes Agent docs: Voice mode
  7. Hermes Agent docs: Vision and image paste
  8. Hermes Agent docs: iMessage via BlueBubbles
  9. Nous Research on X: Meet Hermes Agent (February 25, 2026)
  10. Hermes Agent docs: Session heartbeats and cron watchdogs
  11. Hermes Agent docs: FAQ (Is my data sent anywhere?)
  12. Hermes Agent docs: Installation (desktop packages, install script, Docker)
  13. Hermes Agent docs: Platform support (no Linux desktop package; PyPI installs unsupported)
  14. Hermes Agent docs: Docker setup
  15. Hermes Agent docs: Configuration (terminal backend defaults to local)
  16. Hermes Agent docs: Security (approval modes, optional container isolation)
  17. Hermes Agent docs: Local models
  18. Hermes Agent example config (shared metrics off by default)

ZeroClaw

  1. zeroclaw-labs/zeroclaw on GitHub (MIT OR Apache-2.0, v0.8.7, README)
  2. ZeroClaw website
  3. ZeroClaw docs: Sandboxing
  4. ZeroClaw source: risk presets (Balanced, recommended, has the sandbox on)
  5. ZeroClaw docs: Channels overview (default and standard release bundles)
  6. ZeroClaw docs: You own it (no telemetry)
  7. ZeroClaw docs: Docker and containers
  8. ZeroClaw source: tools (image generation, screenshot, web)

OpenClaw

  1. OpenClaw homepage and Foundation section
  2. OpenClaw integrations: channels, providers and plugins
  3. openclaw/openclaw on GitHub (MIT, v2026.11.1)
  4. OpenClaw docs: Sandboxing (off by default)
  5. Wikipedia: OpenClaw
  6. Notebookcheck: OpenClaw can burn through hundreds of dollars per day
  7. OpenClaw docs: Memory overview
  8. OpenClaw docs: Automations
  9. OpenClaw docs: Chat channels
  10. OpenClaw docs: iMessage
  11. OpenClaw docs: Heartbeat, now a default Proactive check job
  12. OpenClaw docs: Multi-agent routing
  13. OpenClaw docs: Platforms (macOS, Windows, Linux, iOS and Android apps)
  14. OpenClaw docs: Tools (exec, browser, web search)
  15. OpenClaw docs: Audio and voice notes (inbound transcription)
  16. OpenClaw docs: Image and media support (inbound media)
  17. OpenClaw docs: Install (system requirements, installer script, npm, desktop apps, Docker)
  18. OpenClaw docs: One-click deploy on Railway
  19. OpenClaw docs: Usage telemetry and update checks (on by default, feature statistics opt-in)
  20. OpenClaw docs: Ollama provider (local models)

NanoClaw

  1. nanocoai/nanoclaw on GitHub (MIT, README: containers, channels, diagnostics, requirements, models FAQ)
  2. NanoClaw website
  3. NanoClaw docs: Quickstart
  4. NanoClaw docs: Echo hardened runtime
  5. NanoClaw skills: channel, Ollama, OpenCode and Codex installers

Rakazo

  1. Rakazo homepage
  2. Rakazo pricing
  3. Rakazo privacy policy
  4. Rakazo on GitHub (README and license)
  5. Rakazo changelog
  6. Rakazo releases
  7. Rakazo docs: Image and video generation
  8. Rakazo docs: Memory
  9. Rakazo docs: Connect apps
  10. Rakazo docs: Routines
  11. Rakazo docs: Chat apps
  12. Rakazo docs: Messaging apps (self-hosting)
  13. Rakazo docs: Bots and chats (add another bot, bot templates)
  14. Rakazo docs: Groups (several bots in one chat)
  15. Rakazo docs: Mobile app (notifications)
  16. Rakazo privacy policy (updated Sep 14, 2026)
  17. Rakazo privacy policy source on GitHub
  18. Rakazo docs: Logs and monitoring (product analytics off by default)
  19. Rakazo docs: Desktop app (run locally in Docker, updates)
  20. Rakazo docs: Docker computers
  21. Rakazo docs: Self-hosted models (Ollama, LM Studio)
  22. Rakazo Railway template setup guide

NemoClaw

  1. NVIDIA/NemoClaw on GitHub (Apache-2.0, README: supported agents, alpha status)
  2. NemoClaw docs: Overview
  3. NemoClaw docs: Prerequisites and platforms
  4. NemoClaw docs: Choose an inference provider (Ollama, vLLM, NIM)
  5. NemoClaw docs index: messaging channels (WhatsApp, Teams, Google Chat, WeChat experimental)
  6. NemoClaw source: telemetry delivery and NEMOCLAW_DISABLE_TELEMETRY