Published: 2026-08-31

OpenClaw 2.0 review: the upgrade broke, and the new features are web-app only

Two findings here are worth more than the feature list: the in-place upgrade failed the same way it has before, and most of what is new in 2.0 only exists in the web app. The reviewer left OpenClaw for another agent four months ago specifically because updates kept breaking, tried the standard "here is the release link, upgrade yourself" prompt that works on every other open-source tool he runs, and got a silent hang — then abandoned eight months of accumulated memories and skills for a clean install on a different machine. If you use OpenClaw mainly from Telegram or mobile, read the second point carefully before you plan around 2.0.

Source video

"OpenClaw 2.0 just dropped. It's officially over..." by Alex Finn — Watch on YouTube →

Gotchas & Caveats

This is an explicitly critical review from someone who moved off the platform, and he says so up front. The feature descriptions are checkable against the release notes; the verdict is opinion.
The subagent demo did not complete — a task given 27 minutes before recording was still stuck when he returned to it.
The upgrade-breaks pattern is the reviewer's repeated experience, not a measured failure rate. His claim is that roughly 70% of his OpenClaw updates have broken. Treat it as one experienced user's track record, and take the clean-install advice from it regardless — our clean-install walkthrough covers that path.
Group-chat access to a personal agent is a genuine security surface. Permissioning exists; whether it is sufficient for your data is a decision to make deliberately.

Key Takeaways

The in-place upgrade failed silently. Given the release link and asked to upgrade itself — a prompt the reviewer says has a 100% success rate on every other open-source tool he maintains — the agent started, then stopped responding entirely. He ended up doing a fresh install on a different machine and losing eight months of memories and skills rather than repairing it again.
Most 2.0 features are web-app only. Subagent orchestration, widgets and the rest do not surface in Telegram, and the mobile app does not have them either. If a meaningful share of your usage is on a phone, 2.0 changes less for you than the release notes suggest.
Multiplayer agents: your agent can join group chats in Discord or Slack so several people talk to it, with permissioning so participants cannot change passwords or similar. The reviewer declined to demo it on the grounds that he does not want to give other people access to his personal agent — a fair reading of the risk even with permissions in place.
Claude subscriptions work in OpenClaw again, reversing a restriction that had pushed users to other providers.
Automatic skill improvement brings OpenClaw level with the self-improving behaviour Hermes launched on.
Swarm subagents: complex tasks spawn multiple agents and multiple chats, with a tracking view over them.
Conversation forking: you can rewind mid-conversation and branch to try a different approach from that point.
Masked credentials: you can type a password into OpenClaw and it will not be passed to the model, which makes agent-driven site logins workable.
The web app imports Codex projects and chats, so hooked-up coding-agent work appears alongside your OpenClaw sessions in one place — the feature the reviewer rated most useful.

What you can actually set up from this

Extracted from the video's own transcript — the specifics the original summary left out.

Errors & fixes covered

Error: Asked OpenClaw to upgrade itself; it started and then stopped replying

Why it happens: Not diagnosed. He says roughly 70% of his past updates broke, and a sub-agent task he started sat frozen for 48 minutes.

Fix: He did a fresh install on another machine instead; the OpenClaw updates page (per the other video) suggests using a separate coding harness such as Claude or GPT to work through upgrade bugs.

Reproducible steps

What he lists as new in OpenClaw 2.0
Multiplayer agents in Discord or Slack group chats (with new permissioning, such as blocking group members from changing passwords); Claude subscriptions supported again; automatic skill improvement; a better sub-agent experience (it spawned a project in the sidebar and a separate chat per sub-agent, with generated role prompts); forking a conversation; widgets rendered inside the chat; and masked credentials that never reach the model.
Fork a conversation
Right-click a message and choose 'fork from here' to start a new session at that exact point with all earlier context, to try a different approach (his example: vanilla HTML instead of three.js). The fork appears under the original chat.
Use the web app for the new features
Most of the 2.0 features exist only in the OpenClaw web app: they don't show in Telegram or the mobile app. The web app also pulls in your Codex projects and chats so you can see them next to OpenClaw sessions, and shows goals and subtasks in the same style as Codex.

Gotchas

His verdict as of August 2026: Hermes for power users and local models, Grok Bot for zero-config cloud work, and no daily-driver case for OpenClaw because of reliability.
He did not demo multiplayer mode because he doesn't want to give others access to his personal agent.
OpenClaw's strengths in his view: personality, the Codex integration and the sub-agent interface.
Opinions are his; treat the reliability reports as one user's experience.