OpenClaw 2.0发布：简化安装并支持协作Agent

InfoQ Homepage News OpenClaw 2.0 Releases with Simplified Setup and Collaborative Agents AI, ML & Data Engineering OpenClaw 2.0 Releases with Simplified Setup and Collaborative Agents Sep 01, 2026 2 min read by Daniel Dominguez Follow us on Youtube232K Followers Linkedin26K Followers InstagramNew RSS19K Readers X57.1k Followers Facebook21K Likes BlueskyNew 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. The release corresponds to version 2026.8.1 and includes contributions from 933 developers across more than 16,000 pull requests. One of the main changes is a simplified setup process. OpenClaw can now detect resources already available on a user's computer, including ChatGPT or Claude subscriptions, API keys, and locally installed models. The project has reduced the amount of configuration required during installation, moving additional setup into conversations with the agent after it starts running. The browser application has also been rebuilt as a primary interface rather than a secondary control surface. 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. The changes are intended to make the browser a complete way of operating OpenClaw without requiring users to manage most configurations separately. OpenClaw 2.0 also introduces shared cloud sessions for collaborative agent workflows. 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. This extends OpenClaw from primarily personal automation toward shared workflows for families and development teams. The release retains OpenClaw's model-independent architecture. 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. OpenClaw also continues to support communication through channels including WhatsApp, Telegram, Discord, Slack, Signal, and iMessage. OpenClaw operates in a growing category of persistent AI agents. 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. Workflow platforms such as n8n cover some of the same automation use cases but rely more heavily on explicitly configured triggers and workflows. OpenClaw's main architectural distinction remains its self-hosted, model-agnostic approach, leaving users responsible for more of the infrastructure and security configuration. Initial community reaction has been mixed. 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. Team-adjacent voices framed OpenClaw 2.0 as a landmark release after a long pause and a much larger rewrite than planned. OpenClaw’s chief architect Vincent Koc posted: We shipped the biggest lobster ever. 50% of all PRs since project inception in this one release. We waited till the experience on this was out of this world. From UI/UX to local model inference we are now building openclaw with 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. Multiplayer coding + infinite compute with nodes and cloud sessions has been a game changer for how we build. Local harnesses feel like relics of the past now. The release follows an unusually long development period for the project. 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. About the Author Daniel Dominguez Show moreShow less This content is in the AI, ML & Data Engineering topic Related Topics: AI, ML & Data Engineering OpenAI Anthropic Artificial Intelligence ChatGPT Large language models Agents Claude Related Editorial Related Sponsors Popular across InfoQ Kubernetes Promotes KYAML as a Safer, More Consistent Way to Work with Manifests Airbnb Cuts Authentication Code by 60% with Server Driven Architecture OpenClaw 2.0 Releases with Simplified Setup and Collaborative Agents Foundry Model Router Expands from Two Regions to 28, Refreshing Its Model Pool DoorDash’s Flux Runs 130,000 Engineering Tasks through Cloud-Based Agents Scott Jenson on Evolving Desktop OS, Local-First, & Agentic UX The InfoQ Newsletter A round-up of last week’s content on InfoQ sent out every Tuesday. Join a community of over 250,000 senior developers. View an example We protect your privacy.