English

The Best Self-Hosted AI Agents in 2026

Seven self-hosted AI agents ranked on license, local models, sandboxing, telemetry, setup effort and maturity, so you can run a private AI agent on your own hardware.

At a glance

At a glance
BotLicenseChat apps
ZeroClawMIT OR Apache-2.033.3KYesYesTelegram, WhatsApp, DiscordFree
RakazoApache-2.07.5KYesYesTelegram, WhatsApp, iMessage, SlackFrom $10/mo
Hermes AgentMIT261.7KYesNoTelegram, WhatsApp, iMessage, Discord, SlackFrom $20/mo
OpenClawMIT394.2KYesNoTelegram, WhatsApp, iMessage, Discord, SlackFree
NanoClawMIT31.1KYesYesTelegram, WhatsApp, iMessage, Discord, SlackFree
Agent ZeroMIT19.8KYesYesTelegram, WhatsAppFree
nanobotMIT49.9KYesNoTelegram, WhatsApp, Discord, SlackFree
GitHub stars as of Nov 8, 2026

Checklist

Checklist
ZeroClawRakazoHermes AgentOpenClawNanoClawAgent Zeronanobot
Open-source licenseYesYesYesYesYesYesYes
Runs local modelsYesYesYesYesYesYesYes
Sandboxed by defaultYesYesNoNoYesYesNo
No telemetry by defaultYesYesYesNoNoNoYes
Lives in your chat appsYesYesYesYesYesYesYes
Works while you're awayYesYesYesYesYesYesYes

A self-hosted AI agent is only as private as its defaults. Every tool here runs on your own machine or server, but they differ a lot in what happens the first time you start them: whether the agent’s commands run on your host or in a sandbox, whether the software phones home, and how much work it takes to get a bot answering you in a chat app.

How we ranked them

We scored each agent on the six checks in the table above (open license, local models, sandboxed by default, no telemetry by default, lives in chat apps, works while you’re away), then weighed three things the checklist can’t show:

  • Setup effort. A single binary or one script beats a stack you assemble yourself.
  • Safety of defaults. What a fresh install allows before you change anything.
  • Maturity. Release pace, who maintains it, and whether the project calls itself alpha or beta.

“Private” here means your conversations, memory and keys stay on your hardware. Prompts still go to whichever model provider you configure, unless you run a local model; for that angle, see the best local AI agents.

1. ZeroClaw

ZeroClaw is the one we’d hand to someone who wants a private agent without reading a security guide first. It is one Rust binary configured with one TOML file, and its recommended Balanced profile asks before medium-risk actions, blocks high-risk ones, keeps file access inside the workspace and runs tools in an OS sandbox (Seatbelt on macOS, Firejail on Linux), per its sandboxing docs. Its docs state plainly that there is no telemetry and no license server.

The cost is convenience: Slack, iMessage and Signal aren’t in the standard release, so you build from source to get them. It runs on macOS, Linux, Windows, FreeBSD, Android and boards like a Raspberry Pi.

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. Rakazo

Rakazo, which we make, also meets all six checks, with a different shape: instead of one agent, it runs several persistent bots, each with its own memory, routines and a sandboxed computer (browser, terminal and desktop). Self-hosting needs Docker with Compose, curl and OpenSSL; a self-hosted install sends no product analytics unless you configure them. You can use local models through Ollama or LM Studio.

It ranks below ZeroClaw on maturity: the project calls itself beta and releases often. Telegram, WhatsApp and iMessage are available only when self-hosted. See the Rakazo review.

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

3. Hermes Agent

Hermes Agent from Nous Research is the strongest pick if you want a big, active project with no telemetry by default. Conversations, memory and skills live under ~/.hermes, and the metrics it can share with Nous stay off unless you opt in (FAQ). The installer script sets up Python itself, and there are desktop packages for macOS and Windows.

What holds it back here: its terminal backend defaults to local, so commands run on your host unless you switch on container isolation (security docs). Do that before connecting it to email or chat accounts.

Hermes Agent web dashboard Sessions page listing live sessions from cron, Discord, Telegram and the CLI, with rename, export and delete actions
Hermes Agent's dashboard showing sessions across chat platformshermes-agent.nousresearch.com

4. OpenClaw

OpenClaw has the largest ecosystem on the list: 29 chat channels, 64 model and media providers and 142 official plugins, MIT licensed with no paid tier. If you want the most integrations, it wins.

As a self-hosted default, though, it is the loosest of the big names. Sandboxing is off by default, and a daily update check reports your version, OS, Node.js version and CPU architecture to the project’s server (telemetry docs); update.checkOnStart: false turns it off. Our guide Is OpenClaw safe? covers what to change.

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

5. NanoClaw

NanoClaw is the container-first answer to OpenClaw: every agent runs in its own Docker container and sees only the folders you mount, and outbound API calls go through a credential gateway so agents never hold raw keys. The codebase is small enough to read.

It ranks lower on setup and flexibility. It’s built around Claude and Claude Code, there are no config files (you customize your fork by asking Claude Code to edit it), and it sends anonymous setup diagnostics unless you set NANOCLAW_NO_DIAGNOSTICS=1.

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

6. Agent Zero

Agent Zero gives the AI its own Linux computer in Docker, with a terminal, browser, desktop and LibreOffice, isolated from your machine unless you grant host access. It is the oldest project in this ranking (first release June 2024) and still ships often, and a desktop Launcher sets up Docker for you.

Two caveats: code runs in the same container as Agent Zero itself (separate gVisor sandboxes are a v3 prototype), and update checks send your version and a hashed instance ID by default. The image is a full desktop environment, so it needs at least 2 GB of RAM on a server, 4 GB recommended.

Agent Zero web UI showing a request to write a kickoff plan, the agent's collapsed steps for writing and verifying the file in the terminal, and a summary table of the plan
Agent Zero completing a first task in its web UIgithub.com

7. nanobot

nanobot from the University of Hong Kong is the easiest to understand: a small Python core, a polished browser WebUI, no telemetry and installs by script, pip or Docker. It’s a good base if you want to modify an agent rather than just run one.

It sits last because shell commands are not sandboxed by default; bubblewrap or macOS Seatbelt must be turned on, and Windows has no sandbox at all (configuration docs).

nanobot WebUI new-topic screen with Apps, Skills, Automations and Channels in the sidebar, project-grouped topics, and a composer with permission and microphone controls
nanobot's bundled browser WebUIgithub.com

Which one to pick

  • Safest defaults with the least effort: ZeroClaw.
  • Several bots that each need their own computer: Rakazo.
  • Biggest community and ecosystem: Hermes Agent or OpenClaw, with sandboxing turned on.
  • Already run OpenClaw but want isolation: NanoClaw, or wrap OpenClaw in NemoClaw (alpha; see what NemoClaw is).

For more options around one tool, see OpenClaw alternatives and Hermes Agent vs OpenClaw.

Best picks

  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. 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

  3. Hermes Agent

    From $20/mo

    Free, MIT-licensed AI agent from Nous Research that runs on your own machine or server, learns reusable skills, and chats with you on Telegram, Slack and more.

    MIT licensed, no telemetry and lives in your chat apps, but commands aren't sandboxed by default.

    Strengths

    • Free and MIT licensed, and runs on hardware you control
    • Writes and refines its own skills from experience, on top of persistent memory and cross-session search
    • One gateway for 20+ chat platforms, including Telegram, Discord, Slack, WhatsApp, Signal and email
    • Run several separate agents as profiles, each with its own model, memory and skills, and let them talk in group chats
    • Model-agnostic, with a one-command import from OpenClaw

    Weaknesses

    • Setup expects comfort with the command line and with running your own server
    • Model costs are on you unless you use free models, and hosted web search, images and speech need a paid Nous Portal plan or your own keys
    • iMessage needs a separate BlueBubbles server on a Mac
    • No native mobile app; Android support is a command-line install through Termux
    Visit Hermes Agent

  4. 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

  5. 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

  6. Agent Zero

    Free

    Free, MIT-licensed AI agent that runs in its own Docker Linux workspace with a terminal, browser and desktop apps, and chats on Telegram and WhatsApp.

    Runs in its own Docker container with local models, but sends telemetry by default.

    Strengths

    • Free and MIT licensed, with frequent releases (v2.11 to v2.15 between late August and early November 2026)
    • The agent works in its own Linux workspace with a terminal, browser, desktop apps and LibreOffice, isolated from your computer unless you grant host access
    • Web search runs through a local SearXNG instance, and speech-to-text and text-to-speech can run locally
    • Projects keep memory, files, secrets, instructions and model choices separate per job, with workspace snapshots you can roll back
    • Built-in Telegram, WhatsApp and email channels, a scheduler, MCP and a community Plugin Hub with 200+ plugins

    Weaknesses

    • Needs Docker, and the container image is a full Linux desktop environment rather than a small service
    • No built-in image generation; the docs show teaching it an image API yourself
    • By default it checks for updates with Agent Zero's server, sending your version and a hashed instance ID
    • Code runs in the same container as Agent Zero itself today; per-task sandboxes are only a v3 prototype
    • WhatsApp works by linking a phone account through a Baileys bridge, which needs Node.js, rather than the official WhatsApp Business API
    Visit Agent Zero

  7. nanobot

    Free

    Free, MIT-licensed personal AI agent in Python with a browser UI and terminal app, scheduled tasks, memory, and chat on Telegram, Discord, Slack and more.

    Small, readable Python with a good web UI and no telemetry, but shell commands aren't sandboxed by default.

    Strengths

    • Free and MIT licensed, with a small Python core that is meant to be read and modified
    • Polished bundled WebUI with projects, file diffs, an MCP app catalog and an automations calendar, plus a terminal UI
    • Many chat channels, including Telegram, Discord, Slack, WhatsApp, WeChat, Feishu, Teams, Matrix and email
    • Scheduled automations, long-running goals and a heartbeat that reports only useful results to your last chat
    • Works with local models through Ollama, vLLM or LM Studio

    Weaknesses

    • Shell commands are not sandboxed by default; the bubblewrap or macOS Seatbelt sandbox must be turned on, and Windows has none
    • Model costs are on you, and voice messages need a separate transcription provider such as Groq or OpenAI
    • No native mobile or desktop app; on a phone you use the WebUI in a browser or a chat app
    • Missed scheduled runs are not replayed and interrupted subagent tasks are not relaunched after a restart
    Visit nanobot

Features

Features
ZeroClawRakazoHermes AgentOpenClawNanoClawAgent Zeronanobot
Web searchYesYesYesYesYesYesYes
Image generationYesYesYesYesUnknownNoYes
Voice modeYesYesYesYesUnknownYesYes
File uploadsYesYesYesYesYesYesYes
MemoryYesYesYesYesYesYesYes
Takes actions for youYesYesYesYesYesYesYes
App integrationsYesYesYesYesYesYesYes
Works on its ownYesYesYesYesYesYesYes
Messages you firstYesYesYesYesYesYesYes
Runs several botsYesYesYesYesYesYesYes

Sources

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)

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

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)

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

Agent Zero

  1. agent0ai/agent-zero on GitHub (MIT, README, safety model)
  2. Agent Zero releases (v0.2 in June 2024 to v2.15 on November 1, 2026)
  3. Agent Zero homepage
  4. Agent Zero docs: Installation (Launcher, A0 Install, Docker, local models)
  5. Agent Zero docs: VPS deployment (hardware requirements)
  6. Agent Zero model provider list
  7. Agent Zero update check code (version and hashed ID sent to api.agent-zero.ai)
  8. Agent Zero built-in Telegram integration plugin
  9. Agent Zero built-in WhatsApp integration plugin
  10. Agent Zero built-in plugins (scheduler, notify user, email, SearXNG search, Whisper STT, Kokoro TTS)
  11. Agent Zero docs: Memory guide
  12. Agent Zero docs: Agent Profiles
  13. Agent Zero docs: API integration (adding image generation yourself)
  14. Agent Zero v3: A Sneak Peek Inside the Sandbox (August 17, 2026)
  15. Agent Zero LLM API (Venice.ai proxy for A0T token stakers)

nanobot

  1. HKUDS/nanobot on GitHub (MIT, v0.4.1, README)
  2. nanobot documentation
  3. nanobot release archive (officially launched February 2, 2026)
  4. nanobot docs: Chat apps
  5. nanobot docs: Providers and models (Ollama, vLLM, LM Studio)
  6. nanobot docs: Configuration (security, exec sandbox off by default, transcription, Langfuse)
  7. nanobot docs: Automations and heartbeat
  8. nanobot docs: Concepts (heartbeat delivery, subagent recovery)
  9. nanobot docs: Memory and Dream
  10. nanobot docs: Multiple instances
  11. nanobot docs: Deployment (Docker, services, Render)
  12. nanobot source: skills installer runs with DISABLE_TELEMETRY