Futures
Access hundreds of perpetual contracts
TradFi
Gold
One platform for global traditional assets
Options
Hot
Trade European-style vanilla options
Unified Account
Maximize your capital efficiency
Demo Trading
Introduction to Futures Trading
Learn the basics of futures trading
Futures Events
Join events to earn rewards
Demo Trading
Use virtual funds to practice risk-free trading
Launch
CandyDrop
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
Pre-IPOs
Unlock full access to global stock IPOs
Alpha Points
Trade on-chain assets and earn airdrops
Futures Points
Earn futures points and claim airdrop rewards
OpenClaw Founder Responds to Claude CLI "Unban" Rumors: Verbally Allowed but Still Blocked in Practice
According to Beating Monitoring, someone posted a screenshot of the sentence “Anthropic allows OpenClaw-style Claude CLI usage” from the latest OpenClaw documentation on Hacker News, and the post was featured on the front page, then shared on X. OpenClaw founder Peter Steinberger responded on both platforms, providing the clearest version so far: verbal permission is real, but actual blocking is also real.
According to Steinberger, Boris Cherny, head of Claude Code, previously publicly stated on X that CLI usage was permitted. Based on this, OpenClaw re-enabled support and turned off high token-consuming features like heartbeat by default. However, testing by the team showed that Anthropic’s server still blocks OpenClaw’s system prompt snippets, and calls are still rejected. He added that a few renames could bypass the classifier, but he doesn’t want to play this cat-and-mouse game.
OpenClaw connects to Claude Code, which fundamentally involves calling claude -p, the official Claude CLI in a one-time non-interactive mode, with no separate channel to bypass it; whether using an API key or Pro / Max / Team subscription depends on which account was logged into the local Claude CLI at the time. This round of “blocking OpenClaw” by Anthropic is not about banning the claude -p command itself but identifying OpenClaw on the server side through fingerprint recognition and rejecting it when matched. Boris’s verbal “CLI is allowed” and the statement in the documentation about “reusing claude -p by default” refer to the same thing; the only difference with subscription limits is whether a classifier is allowed or not.
OpenClaw removed Claude CLI from the default onboarding for new users in v2026.4.5, but re-added it two days later in v2026.4.7, along with a batch of environment variable cleanups and permission restrictions for the Claude CLI runtime environment. The “re-allowed” mentioned in this documentation corresponds to the changes made in v2026.4.7.