Anthropic - OpenClaw Anthropic staff told us OpenClaw-style Claude CLI usage is allowed again, so OpenClaw treats Claude CLI reuse and claude -p usage as sanctioned unless Anthropic publishes a new policy For long-lived gateway hosts, Anthropic API keys are still the clearest and most predictable production path Anthropic’s current public docs: Claude Code CLI reference Claude Agent SDK overview Using Claude
Anthropic’s New Agent Credits: The End of Compute Arbitrage Anthropic has officially closed the chapter on compute arbitrage As of May 13, 2026, the company is reinstating third-party agent access—including the popular autonomous harness OpenClaw—through a newly introduced “Agent SDK credits” system
Anthropic Unveils Claude Agent SDK Credits to Power Third-Party AI . . . Anthropic is supercharging the developer community by introducing dedicated credits for its Claude Agent SDK This move specifically targets third-party frameworks like OpenClaw, lowering the entry barrier for building autonomous agents The update also features a new 'agent view' for managing multi-agent workflows efficiently
Anthropic Brings Back OpenClaw Agent’s Access to Claude Subscribers This covers usage across Claude Agent SDK, Claude-p, Claude Code GitHub Actions, and third-party apps built on Agent SDK The latter also opens the door to getting usage for OpenClaw tied into Claude subscriptions