2026 年最值得自托管的 OpenClaw 替代品
七款开源 OpenClaw 替代品,按人们离开它的原因排名:默认无沙箱、代码库庞大、遥测和硬件要求。
概览
| 机器人 | 许可证 | 聊天应用 | |||||
|---|---|---|---|---|---|---|---|
| OpenClaw | MIT | 39.4万 | 是 | 否 | Telegram, WhatsApp, iMessage, Discord, Slack | 免费 | |
| ZeroClaw | MIT OR Apache-2.0 | 3.3万 | 是 | 是 | Telegram, WhatsApp, Discord | 免费 | |
| NanoClaw | MIT | 3.1万 | 是 | 是 | Telegram, WhatsApp, iMessage, Discord, Slack | 免费 | |
| Hermes Agent | MIT | 26.2万 | 是 | 否 | Telegram, WhatsApp, iMessage, Discord, Slack | US$20/月起 | |
| Rakazo | Apache-2.0 | 7538 | 是 | 是 | Telegram, WhatsApp, iMessage, Slack | US$10/月起 | |
| NemoClaw | Apache-2.0 | 2.3万 | 是 | 是 | Telegram, Discord, Slack | 免费 | |
| PicoClaw | MIT | 3万 | 是 | 否 | Telegram, WhatsApp, Discord, Slack | 免费 | |
| nanobot | MIT | 5万 | 是 | 否 | Telegram, WhatsApp, Discord, Slack | 免费 |
检查清单
OpenClaw 是默认的开源智能体:采用 MIT 许可证,截至 2026 年 11 月 8 日有 394,193 颗 GitHub 星,29 个聊天渠道,并为所有桌面和手机平台提供应用。大多数寻找替代品的人并不是不满意它的能力,而是对它的做事方式感到不安。
人们为什么离开 OpenClaw
常被提到的原因有四个,它们决定了下面的排名。
默认没有沙箱。 OpenClaw 的沙箱开箱即关闭,所以除非你自己开启审批或沙箱,否则智能体会在你的主机上运行命令。再加上它能访问你的邮件、消息和第三方技能,提示注入就成了真实的风险。它自己的维护者也警告说,对非技术用户来说它有风险。我们在 OpenClaw 安全吗?中有更详细的介绍。
体量与复杂度。 142 个官方插件以及 64 个模型和媒体提供商让它能力很强,但这意味着有大量代码需要信任和持续更新,而且安装过程默认你会用命令行。
遥测。 它默认每天联系项目服务器,发送你的 OpenClaw 版本、操作系统、Node.js 版本和 CPU 架构,外加安装计数和更新报告。影响不大,update.checkOnStart: false 就能关闭,但在你关闭之前它一直开着。
硬件与运行时。 它需要 Node 24.16+ 或 26.1+,在笔记本上没问题,在树莓派或路由器上就没那么理想了。
我们按照这些替代品能解决多少上述问题来排名,同时它们仍要完成核心任务:一个你通过聊天应用对话的常驻智能体。
1. ZeroClaw:最接近“默认安全的 OpenClaw”
ZeroClaw 解决了全部四个问题。它是单个 Rust 二进制文件,只有一个 TOML 配置文件,可运行在 macOS、Linux、Windows、FreeBSD、Android 或树莓派上。它推荐的 Balanced 配置会在中风险操作前询问、阻止高风险操作、把文件访问限制在工作区内,并在操作系统沙箱中运行工具(macOS 上是 Seatbelt,Linux 上是 Firejail)。它的文档声明不发送任何遥测。
问题在于渠道:Slack、iMessage 和 Signal 不在标准发行版中,你需要启用额外功能从源码构建。如果你主要用 WhatsApp、Telegram 或 Discord,这就无关紧要。完整对比:ZeroClaw vs OpenClaw。

2. NanoClaw:真正的容器隔离,小巧的代码库
NanoClaw 起初是 OpenClaw 的一个更小、带容器隔离的版本。每个智能体运行在自己的 Docker 容器中,只能看到你挂载的文件夹,外发的 API 调用会经过一个凭据网关,所以智能体从不持有原始密钥。主机端只有一个 Node 进程和少量文件。
它排在 ZeroClaw 之后有两个原因:它围绕 Claude 和 Claude Code 构建(定制意味着让 Claude Code 修改你的 fork,没有配置文件),而且除非你设置 NANOCLAW_NO_DIAGNOSTICS=1,否则它会发送匿名的安装诊断数据。参见 NanoClaw vs OpenClaw。

3. Hermes Agent:迁移最轻松
Nous Research 的 Hermes Agent 在设计时就考虑到了 OpenClaw 用户。它能用一条命令导入你的 OpenClaw 设置、记忆和技能,覆盖 20 多个聊天平台,共享指标默认关闭。它还增加了 OpenClaw 并不主打的能力:在完成复杂任务后自己编写并完善技能。
不过它没有解决沙箱问题。终端后端默认是本地,容器隔离是可选的。选它是为了遥测和功能,而不是安全。更多内容请见 Hermes vs OpenClaw。

4. Rakazo:每个机器人一台沙箱电脑
Rakazo(我们开发的产品)为每个机器人提供一台独立的沙箱电脑,带浏览器、终端和桌面,所以智能体的命令在那里运行,而不是在你的主机上。它采用 Apache-2.0 许可证,自托管安装不发送产品分析数据,并可通过 Ollama 或 LM Studio 运行本地模型。哪些操作需要你批准由你来设定。
它比上面几款更重(需要 Docker Engine 和 Compose),仍处于 beta 阶段,而且 Telegram、WhatsApp 和 iMessage 只有在自托管时才能使用。

5. NemoClaw:保留 OpenClaw,加一个笼子
如果你喜欢 OpenClaw,只是不想让它在你的机器上毫无约束地运行,NemoClaw 是 NVIDIA 用来在 OpenShell 沙箱中运行 OpenClaw 的技术栈。未经批准的网络目标在操作员批准之前都会被拦截,凭据也保存在沙箱之外。
它会让另外三个问题变得更糟:至少 8 GB 内存(推荐 16 GB)、需要容器运行时、除非设置 NEMOCLAW_DISABLE_TELEMETRY=1 否则会向 NVIDIA 发送遥测,而且处于 alpha 阶段。参见 NemoClaw vs OpenClaw。

6. PicoClaw:适合极小的硬件
Sipeed 的 PicoClaw 是单个 Go 二进制文件,至少需要 10 MB 可用内存(推荐 32 MB 以上),可运行在 x86、ARM、RISC-V 和 MIPS 上,包括 10 美元的开发板、路由器和旧 Android 手机。文档中没有提到遥测,支持大约 19 个聊天渠道。
它入选只是因为硬件。进程隔离默认关闭,项目自己也说在 v1.0 之前不要用于生产环境。

7. nanobot:小巧易读的 Python
香港大学数据智能实验室的 nanobot 是一个紧凑的 Python 智能体,有精致的浏览器界面、终端界面、定时自动化和众多聊天渠道。它没有遥测,支持 Ollama、vLLM 或 LM Studio。
和 OpenClaw 一样,在你开启 bubblewrap 或 Seatbelt 之前,它的 shell 命令不在沙箱中运行,而 Windows 上根本没有沙箱。如果你想要一个一下午就能读完的代码库,就选它。

该选哪个
- 想要 OpenClaw 的功能,同时具备安全默认值且无遥测:ZeroClaw。
- 想让每个智能体都在容器中,并且不介意 Claude Code:NanoClaw。
- 想保留你的 OpenClaw 配置并停止遥测:Hermes Agent。
- 想继续用 OpenClaw 本身并放进沙箱,而且内存充足:NemoClaw。
- 在开发板或旧手机上运行:PicoClaw。
想看一份不以 OpenClaw 为中心的更全面列表,请参阅最佳自托管 AI 智能体。
替代品
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.
访问 ZeroClaw优点
- 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
缺点
- 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
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.
访问 NanoClaw优点
- 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
缺点
- 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
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.
访问 Hermes Agent优点
- 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
缺点
- 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
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.
访问 Rakazo优点
- 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
缺点
- 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
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.
访问 NemoClaw优点
- 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
缺点
- 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
Free, MIT-licensed personal AI agent written in Go that runs as one small binary on cheap boards, old phones and PCs, and chats on Telegram, Discord and more.
Runs on cheap boards in a few dozen MB of RAM with no telemetry, but it's pre-1.0 and commands aren't sandboxed by default.
访问 PicoClaw优点
- Tiny footprint: one Go binary that Sipeed says boots in under a second and needs only 10 to 20 MB of RAM
- Runs on hardware others can't, from $10 RISC-V boards and routers to old Android phones
- About 19 chat channels, including Telegram, Discord, Slack, WhatsApp, Matrix, LINE and Delta Chat
- Web search works without an API key through a built-in DuckDuckGo fallback
- Heartbeat check-ins, cron reminders, MCP tools and routing between several agents
缺点
- The project warns it is in early rapid development, may have unresolved security issues, and should not be used in production before v1.0
- The default workspace restriction only checks paths; true process isolation is off by default and implemented only on Linux and Windows
- Native WhatsApp needs a custom build or a separate bridge
- No built-in image generation, and voice messages are only transcribed if you add a provider such as Groq
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.
访问 nanobot优点
- 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
缺点
- 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
功能
来源
OpenClaw
- OpenClaw homepage and Foundation section
- OpenClaw integrations: channels, providers and plugins
- openclaw/openclaw on GitHub (MIT, v2026.11.1)
- OpenClaw docs: Sandboxing (off by default)
- Wikipedia: OpenClaw
- Notebookcheck: OpenClaw can burn through hundreds of dollars per day
- OpenClaw docs: Memory overview
- OpenClaw docs: Automations
- OpenClaw docs: Chat channels
- OpenClaw docs: iMessage
- OpenClaw docs: Heartbeat, now a default Proactive check job
- OpenClaw docs: Multi-agent routing
- OpenClaw docs: Platforms (macOS, Windows, Linux, iOS and Android apps)
- OpenClaw docs: Tools (exec, browser, web search)
- OpenClaw docs: Audio and voice notes (inbound transcription)
- OpenClaw docs: Image and media support (inbound media)
- OpenClaw docs: Install (system requirements, installer script, npm, desktop apps, Docker)
- OpenClaw docs: One-click deploy on Railway
- OpenClaw docs: Usage telemetry and update checks (on by default, feature statistics opt-in)
- OpenClaw docs: Ollama provider (local models)
ZeroClaw
- zeroclaw-labs/zeroclaw on GitHub (MIT OR Apache-2.0, v0.8.7, README)
- ZeroClaw website
- ZeroClaw docs: Sandboxing
- ZeroClaw source: risk presets (Balanced, recommended, has the sandbox on)
- ZeroClaw docs: Channels overview (default and standard release bundles)
- ZeroClaw docs: You own it (no telemetry)
- ZeroClaw docs: Docker and containers
- ZeroClaw source: tools (image generation, screenshot, web)
NanoClaw
Hermes Agent
- NousResearch/hermes-agent on GitHub (MIT, v0.23.0)
- Hermes Agent homepage and Nous Portal pricing
- Hermes Agent documentation
- Hermes Agent docs: Profiles, running multiple agents
- Hermes Agent docs: Bot Mode
- Hermes Agent docs: Voice mode
- Hermes Agent docs: Vision and image paste
- Hermes Agent docs: iMessage via BlueBubbles
- Nous Research on X: Meet Hermes Agent (February 25, 2026)
- Hermes Agent docs: Session heartbeats and cron watchdogs
- Hermes Agent docs: FAQ (Is my data sent anywhere?)
- Hermes Agent docs: Installation (desktop packages, install script, Docker)
- Hermes Agent docs: Platform support (no Linux desktop package; PyPI installs unsupported)
- Hermes Agent docs: Docker setup
- Hermes Agent docs: Configuration (terminal backend defaults to local)
- Hermes Agent docs: Security (approval modes, optional container isolation)
- Hermes Agent docs: Local models
- Hermes Agent example config (shared metrics off by default)
Rakazo
- Rakazo homepage
- Rakazo pricing
- Rakazo privacy policy
- Rakazo on GitHub (README and license)
- Rakazo changelog
- Rakazo releases
- Rakazo docs: Image and video generation
- Rakazo docs: Memory
- Rakazo docs: Connect apps
- Rakazo docs: Routines
- Rakazo docs: Chat apps
- Rakazo docs: Messaging apps (self-hosting)
- Rakazo docs: Bots and chats (add another bot, bot templates)
- Rakazo docs: Groups (several bots in one chat)
- Rakazo docs: Mobile app (notifications)
- Rakazo privacy policy (updated Sep 14, 2026)
- Rakazo privacy policy source on GitHub
- Rakazo docs: Logs and monitoring (product analytics off by default)
- Rakazo docs: Desktop app (run locally in Docker, updates)
- Rakazo docs: Docker computers
- Rakazo docs: Self-hosted models (Ollama, LM Studio)
- Rakazo Railway template setup guide
NemoClaw
- NVIDIA/NemoClaw on GitHub (Apache-2.0, README: supported agents, alpha status)
- NemoClaw docs: Overview
- NemoClaw docs: Prerequisites and platforms
- NemoClaw docs: Choose an inference provider (Ollama, vLLM, NIM)
- NemoClaw docs index: messaging channels (WhatsApp, Teams, Google Chat, WeChat experimental)
- NemoClaw source: telemetry delivery and NEMOCLAW_DISABLE_TELEMETRY
PicoClaw
- sipeed/picoclaw on GitHub (MIT, README with security notice and channel list)
- PicoClaw releases (v0.0.1 on February 9, 2026; v0.3.1 on July 3, 2026)
- PicoClaw official website and downloads
- PicoClaw docs: Configuration (workspace restriction, heartbeat, voice, multi-agent routing)
- PicoClaw source: subprocess isolation, disabled by default
- PicoClaw docs: Tools configuration (web search, exec, cron, MCP, skills)
- PicoClaw docs: Chat apps (WhatsApp native build or bridge)
- PicoClaw docs: Hardware compatibility and minimum requirements
- PicoClaw docs: Docker
nanobot
- HKUDS/nanobot on GitHub (MIT, v0.4.1, README)
- nanobot documentation
- nanobot release archive (officially launched February 2, 2026)
- nanobot docs: Chat apps
- nanobot docs: Providers and models (Ollama, vLLM, LM Studio)
- nanobot docs: Configuration (security, exec sandbox off by default, transcription, Langfuse)
- nanobot docs: Automations and heartbeat
- nanobot docs: Concepts (heartbeat delivery, subagent recovery)
- nanobot docs: Memory and Dream
- nanobot docs: Multiple instances
- nanobot docs: Deployment (Docker, services, Render)
- nanobot source: skills installer runs with DISABLE_TELEMETRY







