| 维度 / 指标 | ![]() | ![]() |
|---|---|---|
| 官方域名 | openclaw.ai | flowith.io |
| 定价模式 | 付费,免费 | 定价请咨询 |
| 月访问量 | 190.31万 (1,903,068) | 32.47万 (324,679) |
| 月度环比流量变化 | -64.76万 (-25.4%) | -12.22万 (-27.3%) |
| 主要市场与份额 | 🇺🇸 美国 (19.3%) | 🇨🇳 中国 (24.1%) |
| 直接访问 / 月 | 59.64万 | 17.12万 |
| 用户评分 | 4.6 | 4.4 |
| 支持的平台 | 网站 | 网站 |

运行在你自己机器上、可从聊天应用操控的开源个人 AI 助理
天生自托管,记忆、技能、模型和数据都不会离开你掌控的基础设施。
通过 WhatsApp、Telegram 或你已在用的其他客户端操作助理,无需再学一个新后台。
代理可以整理收件箱、发送邮件、管理日历、处理值机等实际操作。
用技能和插件扩展能力,并保留跨对话延续的上下文。

为深度工作打造的智能体 AI 工作空间画布
把提示词、输出与智能体运行结果作为可连接的节点铺在无限画布上,复杂项目不再随滚动而迷失。
在同一界面使用多个领先大模型,按任务切换,或并排对比不同模型的回答。
把多步骤目标交给智能体,由它自行规划、搜集信息并产出交付物,减少反复提示。
将笔记、参考资料与生成成果存入可持续检索的知识空间,供后续项目复用。
Cloud-based autonomous agent platform executing multi-step goals, but lacks self-hosted local deployment.

提供协作型可视化画布与 AI 图表生成器,但缺乏多模型聊天和自主智能体执行功能。

免费 / 开源Open WebUI is an open-source, self-hosted AI interface that lets individuals and organizations run any model — local or cloud — inside a workspace they fully control. It ships as a one-command install, supports Ollama, OpenAI-compatible and Anthropic endpoints, and extends through Python tools, functions and pipelines.
免费 / 开源Open WebUI is an open-source, self-hosted AI interface that lets individuals and organizations run any model — local or cloud — inside a workspace they fully control. It ships as a one-command install, supports Ollama, OpenAI-compatible and Anthropic endpoints, and extends through Python tools, functions and pipelines.

专项更强Open-source desktop AI workforce designed for executing complex browser, file, and terminal tasks.
Generates automated AI agents and business apps from text, but uses structured task lists instead of spatial canvases.
免费 / 开源AnythingLLM is a free, open-source AI assistant that runs on your own computer or server: chat with documents, transcribe and summarize meetings, run background jobs, use web search and connect any LLM provider — without accounts, API keys or token limits.
免费 / 开源AnythingLLM is a free, open-source AI assistant that runs on your own computer or server: chat with documents, transcribe and summarize meetings, run background jobs, use web search and connect any LLM provider — without accounts, API keys or token limits.
使用基于节点的画布来让 AI 智能体生成多媒体,但缺乏 Flowith 更广泛的头脑风暴与文档处理功能。