2026-09-02
每日一文 · 长文精读
OpenClaw 2.0 Releases with Simplified Setup and Collaborative Agents
OpenClaw 2.0 发布：简化设置并引入协作智能体
作者：Daniel Dominguez · InfoQ 原文
摘要：OpenClaw 2.0 是开源个人AI智能体的重大更新，简化了安装流程（自动检测现有资源），重建了浏览器界面作为主要交互入口，并引入共享云会话以支持多用户协作工作流。该版本保留了模型无关架构，支持多种通信渠道。社区反应不一，部分用户报告顺利升级，另一些则遇到迁移、网关、自动化丢失或模型认证问题。开发周期异常长，涉及大量重构。
OpenClaw has released OpenClaw 2.0, a major update to the open-source personal AI agent that changes its installation process, browser interface, memory, skills, automations, plugins, security, and collaboration features.
OpenClaw 发布了 OpenClaw 2.0，这是对开源个人 AI 智能体的重大更新，改变了其安装流程、浏览器界面、记忆、技能、自动化、插件、安全性和协作功能。
The release corresponds to version 2026.8.1 and includes contributions from 933 developers across more than 16,000 pull requests.
该版本对应 2026.8.1，包含来自 933 名开发者的贡献，涉及超过 16,000 个拉取请求。
One of the main changes is a simplified setup process.
主要变化之一是简化的设置流程。
OpenClaw can now detect resources already available on a user's computer, including ChatGPT or Claude subscriptions, API keys, and locally installed models.
OpenClaw 现在可以检测用户计算机上已有的资源，包括 ChatGPT 或 Claude 订阅、API 密钥以及本地安装的模型。
The project has reduced the amount of configuration required during installation, moving additional setup into conversations with the agent after it starts running.
该项目减少了安装期间所需的配置量，将额外的设置转移到智能体启动运行后的对话中。
The browser application has also been rebuilt as a primary interface rather than a secondary control surface.
浏览器应用也被重建为主要界面，而非次要控制面板。
Users now enter directly into a conversation with their agent and can configure it, monitor ongoing tasks, and interact with workflows from the same interface.
用户现在可以直接进入与智能体的对话，并在同一界面中配置它、监控正在进行的任务以及与工作流交互。
The changes are intended to make the browser a complete way of operating OpenClaw without requiring users to manage most configurations separately.
这些变化旨在使浏览器成为操作 OpenClaw 的完整方式，无需用户单独管理大部分配置。
OpenClaw 2.0 also introduces shared cloud sessions for collaborative agent workflows.
OpenClaw 2.0 还引入了共享云会话，用于协作智能体工作流。
Multiple users can participate in an existing agent session while retaining its context, allowing a task to be shared or handed from one person to another.
多个用户可以参与现有的智能体会话，同时保留其上下文，从而允许任务在人与人之间共享或交接。
This extends OpenClaw from primarily personal automation toward shared workflows for families and development teams.
这将 OpenClaw 从主要面向个人自动化扩展到面向家庭和开发团队的共享工作流。
The release retains OpenClaw's model-independent architecture.
该版本保留了 OpenClaw 的模型无关架构。
It can work with hosted models, existing AI subscriptions, API-based providers, and local models, while state can remain on infrastructure controlled by the user.
它可以与托管模型、现有 AI 订阅、基于 API 的提供商和本地模型一起工作，同时状态可以保留在用户控制的基础设施上。
OpenClaw also continues to support communication through channels including WhatsApp, Telegram, Discord, Slack, Signal, and iMessage.
OpenClaw 还继续支持通过 WhatsApp、Telegram、Discord、Slack、Signal 和 iMessage 等渠道进行通信。
OpenClaw operates in a growing category of persistent AI agents.
OpenClaw 属于一个不断增长的持久 AI 智能体类别。
Hermes Agent provides a similar open-source approach centered on persistent memory and cross-platform messaging, while managed systems such as ChatGPT Agent and Grok Bot provide computer and browser-based task execution through vendor-hosted infrastructure.
Hermes Agent 提供了一种类似的、以持久内存和跨平台消息传递为中心的开源方法，而 ChatGPT Agent 和 Grok Bot 等托管系统则通过供应商托管的基础设施提供基于计算机和浏览器的任务执行。
Workflow platforms such as n8n cover some of the same automation use cases but rely more heavily on explicitly configured triggers and workflows.
n8n 等工作流平台涵盖了部分相同的自动化用例，但更依赖于显式配置的触发器和流程。
OpenClaw's main architectural distinction remains its self-hosted, model-agnostic approach, leaving users responsible for more of the infrastructure and security configuration.
OpenClaw 的主要架构区别仍然是其自托管、模型无关的方法，让用户负责更多的基础设施和安全配置。
Initial community reaction has been mixed.
最初的社区反应褒贬不一。
Some users reported smooth upgrades and welcomed the new release, while others experienced migration problems, broken gateways, lost automations, or model authentication issues after updating.
一些用户报告升级顺利并欢迎新版本，而另一些用户在更新后遇到了迁移问题、网关故障、自动化丢失或模型认证问题。
Team-adjacent voices framed OpenClaw 2.0 as a landmark release after a long pause and a much larger rewrite than planned.
接近团队的声音将 OpenClaw 2.0 描述为长期停顿后的里程碑式版本，并且重写规模远超计划。
OpenClaw’s Chief Architect Vincent Koc posted: We shipped the biggest lobster ever.
OpenClaw 的首席架构师 Vincent Koc 发帖说：我们发布了有史以来最大的龙虾。
50% of all PRs since project inception in this one release.
自项目启动以来 50% 的拉取请求都集中在这个版本中。
We waited till the experience on this was out of this world.
我们一直等到这个体验超凡脱俗。
From UI/UX to local model inference we are now building openclaw with openclaw.
从 UI/UX 到本地模型推理，我们现在正在用 OpenClaw 构建 OpenClaw。
Meanwhile OpenClaw’s creator Peter Steinberger commented: Two months ago, we started the mission to “build OpenClaw with OpenClaw,” and bit by bit, we moved everyone from using their local coding harness to using http://team.openclaw.ai - our shared agent that knows what everyone’s working on and orchestrates it all.
与此同时，OpenClaw 的创始人 Peter Steinberger 评论道：两个月前，我们开始了“用 OpenClaw 构建 OpenClaw”的使命，并逐步将每个人从使用本地编码工具转移到使用 http://team.openclaw.ai —— 我们的共享智能体，它知道每个人在做什么并协调一切。
Multiplayer coding + infinite compute with nodes and cloud sessions has been a game changer for how we build.
多人编码 + 无限计算（通过节点和云会话）彻底改变了我们的构建方式。
Local harnesses feel like relics of the past now.
本地工具现在感觉像是过去的遗物。
The release follows an unusually long development period for the project.
该版本经历了该项目异常长的开发周期。
OpenClaw says it previously shipped 106 releases over 230 days, but development of this update lasted nearly seven weeks as changes originally focused on installation and the browser interface expanded into a broader restructuring of the project.
OpenClaw 表示，此前在 230 天内发布了 106 个版本，但此次更新的开发持续了近七周，因为最初专注于安装和浏览器界面的变化扩展为更广泛的项目重组。
阅读理解
1. What is one of the main changes in OpenClaw 2.0?
2. How does OpenClaw 2.0 enable collaborative workflows?
3. What was the community reaction to OpenClaw 2.0?