한국어

2026년 최고의 셀프 호스팅 AI 에이전트

라이선스, 로컬 모델, 샌드박싱, 텔레메트리, 설정 난이도, 성숙도로 순위를 매긴 7개 셀프 호스팅 AI 에이전트. 내 하드웨어에서 비공개 AI 에이전트를 실행하세요.

한눈에 보기

한눈에 보기
봇라이선스메신저 앱
ZeroClawMIT OR Apache-2.03.3만예예Telegram, WhatsApp, Discord무료
RakazoApache-2.07.5천예예Telegram, WhatsApp, iMessage, Slack월 US$10부터
Hermes AgentMIT26.2만예아니요Telegram, WhatsApp, iMessage, Discord, Slack월 US$20부터
OpenClawMIT39.4만예아니요Telegram, WhatsApp, iMessage, Discord, Slack무료
NanoClawMIT3.1만예예Telegram, WhatsApp, iMessage, Discord, Slack무료
Agent ZeroMIT2만예예Telegram, WhatsApp무료
nanobotMIT5만예아니요Telegram, WhatsApp, Discord, Slack무료
2026. 11. 8. 기준 GitHub 스타

체크리스트

체크리스트
ZeroClawRakazoHermes AgentOpenClawNanoClawAgent Zeronanobot
오픈 소스 라이선스예예예예예예예
로컬 모델 실행예예예예예예예
기본 샌드박스예예아니요아니요예예아니요
기본 텔레메트리 없음예예예아니요아니요아니요예
메신저 앱에서 사용예예예예예예예
자리를 비워도 작업예예예예예예예

셀프 호스팅 AI 에이전트의 개인정보 보호 수준은 기본값만큼입니다. 여기 있는 모든 도구는 자신의 컴퓨터나 서버에서 실행되지만, 처음 시작할 때 일어나는 일은 크게 다릅니다. 에이전트의 명령이 호스트에서 실행되는지 샌드박스에서 실행되는지, 소프트웨어가 외부로 정보를 보내는지, 그리고 채팅 앱에서 봇이 답하게 만들기까지 얼마나 많은 작업이 필요한지입니다.

순위 기준

위 표의 여섯 가지 항목(오픈 라이선스, 로컬 모델, 기본 샌드박스, 기본 텔레메트리 없음, 채팅 앱에서 사용, 자리를 비운 동안 작업)으로 각 에이전트를 평가한 뒤, 체크리스트로는 드러나지 않는 세 가지를 따졌습니다.

  • 설정 난이도. 단일 바이너리나 스크립트 하나가 직접 조립하는 스택보다 낫습니다.
  • 기본값의 안전성. 아무것도 바꾸기 전에 새 설치가 허용하는 것입니다.
  • 성숙도. 릴리스 속도, 유지보수 주체, 그리고 프로젝트가 스스로를 알파나 베타라고 부르는지입니다.

여기서 “비공개”란 대화, 메모리, 키가 내 하드웨어에 머문다는 뜻입니다. 로컬 모델을 실행하지 않는 한 프롬프트는 여전히 설정한 모델 제공자로 전송됩니다. 그 관점은 최고의 로컬 AI 에이전트를 참고하세요.

1. ZeroClaw

ZeroClaw는 보안 가이드를 먼저 읽지 않고도 비공개 에이전트를 원하는 사람에게 건네고 싶은 도구입니다. TOML 파일 하나로 설정하는 Rust 바이너리 하나이며, 샌드박싱 문서에 따르면 권장 Balanced 프로필은 중간 위험 작업 전에 묻고, 고위험 작업은 차단하며, 파일 접근을 워크스페이스 안으로 제한하고, 도구를 OS 샌드박스(macOS에서는 Seatbelt, Linux에서는 Firejail)에서 실행합니다. 문서는 텔레메트리도 라이선스 서버도 없다고 분명히 밝힙니다.

대가는 편의성입니다. Slack, iMessage, Signal은 표준 릴리스에 포함되지 않아 소스에서 빌드해야 합니다. macOS, Linux, Windows, FreeBSD, Android, 그리고 Raspberry Pi 같은 보드에서 실행됩니다.

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

저희가 만드는 Rakazo도 여섯 가지 항목을 모두 충족하지만 형태가 다릅니다. 에이전트 하나 대신 여러 지속형 봇을 실행하며, 각 봇은 자체 메모리, 루틴, 샌드박스 컴퓨터(브라우저, 터미널, 데스크톱)를 가집니다. 셀프 호스팅에는 Compose가 있는 Docker, curl, OpenSSL이 필요하며, 셀프 호스팅 설치는 직접 설정하지 않는 한 제품 분석 데이터를 보내지 않습니다. Ollama나 LM Studio로 로컬 모델을 쓸 수 있습니다.

성숙도에서 ZeroClaw보다 낮습니다. 프로젝트가 스스로 베타라고 부르며 릴리스가 잦습니다. Telegram, WhatsApp, iMessage는 셀프 호스팅할 때만 사용할 수 있습니다. Rakazo 리뷰를 참고하세요.

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

Nous Research의 Hermes Agent는 기본 텔레메트리 없이 크고 활발한 프로젝트를 원한다면 가장 강력한 선택입니다. 대화, 메모리, 스킬은 ~/.hermes 아래에 있고, Nous와 공유할 수 있는 지표는 옵트인하지 않는 한 꺼져 있습니다(FAQ). 설치 스크립트가 Python을 직접 설정하며, macOS와 Windows용 데스크톱 패키지도 있습니다.

여기서 발목을 잡는 점은 터미널 백엔드의 기본값이 local이라는 것입니다. 컨테이너 격리를 켜지 않으면 명령이 호스트에서 실행됩니다(보안 문서). 이메일이나 채팅 계정에 연결하기 전에 켜세요.

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

OpenClaw는 목록에서 가장 큰 생태계를 가지고 있습니다. 29개 채팅 채널, 64개 모델 및 미디어 제공자, 142개 공식 플러그인이 있고, 유료 요금제 없는 MIT 라이선스입니다. 통합 기능이 가장 많은 것을 원한다면 OpenClaw가 이깁니다.

하지만 셀프 호스팅 기본값으로는 대형 프로젝트 중 가장 느슨합니다. 샌드박싱은 기본적으로 꺼져 있고, 매일 업데이트 확인이 버전, OS, Node.js 버전, CPU 아키텍처를 프로젝트 서버에 보고합니다(텔레메트리 문서). update.checkOnStart: false로 끌 수 있습니다. 무엇을 바꿔야 하는지는 OpenClaw는 안전한가? 가이드에서 다룹니다.

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

5. NanoClaw

NanoClaw는 컨테이너 우선으로 OpenClaw에 답한 도구입니다. 모든 에이전트가 자체 Docker 컨테이너에서 실행되어 마운트한 폴더만 보고, 외부 API 호출은 자격 증명 게이트웨이를 거치므로 에이전트가 원시 키를 보유하지 않습니다. 코드베이스는 읽을 수 있을 만큼 작습니다.

설정과 유연성에서 점수가 낮습니다. Claude와 Claude Code를 중심으로 만들어졌고, 설정 파일이 없으며(Claude Code에게 포크를 수정하도록 요청해 커스터마이즈합니다), NANOCLAW_NO_DIAGNOSTICS=1을 설정하지 않으면 익명 설정 진단 정보를 보냅니다.

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 Zero는 AI에게 터미널, 브라우저, 데스크톱, LibreOffice가 있는 Docker 속 자체 Linux 컴퓨터를 주며, 호스트 접근을 허용하지 않는 한 내 컴퓨터와 격리됩니다. 이 순위에서 가장 오래된 프로젝트이지만(첫 릴리스 2024년 6월) 여전히 자주 릴리스되며, 데스크톱 Launcher가 Docker를 대신 설정해 줍니다.

단서가 두 가지 있습니다. 코드가 Agent Zero 자체와 같은 컨테이너에서 실행되고(별도의 gVisor 샌드박스는 v3 프로토타입입니다), 업데이트 확인이 기본적으로 버전과 해시된 인스턴스 ID를 보냅니다. 이미지가 전체 데스크톱 환경이므로 서버에 최소 2 GB RAM이 필요하며 4 GB를 권장합니다.

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

홍콩대학교의 nanobot은 이해하기 가장 쉽습니다. 작은 Python 코어, 세련된 브라우저 WebUI, 텔레메트리 없음, 그리고 스크립트, pip, Docker로 설치합니다. 에이전트를 단순히 실행하기보다 수정하고 싶다면 좋은 기반입니다.

최하위인 이유는 셸 명령이 기본적으로 샌드박스되지 않기 때문입니다. bubblewrap이나 macOS Seatbelt를 켜야 하며, Windows에는 샌드박스가 아예 없습니다(설정 문서).

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

무엇을 고를까

  • 최소한의 노력으로 가장 안전한 기본값: ZeroClaw.
  • 각자 자기 컴퓨터가 필요한 여러 봇: Rakazo.
  • 가장 큰 커뮤니티와 생태계: 샌드박싱을 켠 Hermes Agent 또는 OpenClaw.
  • 이미 OpenClaw를 쓰지만 격리를 원함: NanoClaw, 또는 OpenClaw를 NemoClaw로 감싸기(알파, NemoClaw란 무엇인가 참고).

특정 도구를 중심으로 한 더 많은 선택지는 OpenClaw 대안과 Hermes Agent vs OpenClaw를 참고하세요.

추천

  1. ZeroClaw

    무료

    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.

    장점

    • 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

    단점

    • 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
    ZeroClaw 방문

  2. Rakazo

    월 US$10부터

    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.

    장점

    • 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

    단점

    • 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
    Rakazo 방문

  3. Hermes Agent

    월 US$20부터

    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.

    장점

    • 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

    단점

    • 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
    Hermes Agent 방문

  4. OpenClaw

    무료

    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.

    장점

    • 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

    단점

    • 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
    OpenClaw 방문

  5. NanoClaw

    무료

    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.

    장점

    • 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

    단점

    • 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
    NanoClaw 방문

  6. Agent Zero

    무료

    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.

    장점

    • 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

    단점

    • 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
    Agent Zero 방문

  7. nanobot

    무료

    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.

    장점

    • 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

    단점

    • 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
    nanobot 방문

기능

기능
ZeroClawRakazoHermes AgentOpenClawNanoClawAgent Zeronanobot
웹 검색예예예예예예예
이미지 생성예예예예알 수 없음아니요예
음성 모드예예예예알 수 없음예예
파일 업로드예예예예예예예
메모리예예예예예예예
대신 작업 수행예예예예예예예
앱 연동예예예예예예예
스스로 작업예예예예예예예
먼저 메시지를 보냄예예예예예예예
여러 봇 운영예예예예예예예

출처

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