Anthropic bans OAuth tokens (including Agent SDK) in 3P tools
1–10 of 10 posts
Re: Anthropic bans OAuth tokens (including Agent SDK) in 3P tools
#2Using OAuth tokens from Claude Code/Claude.ai in third party tools such as OpenClaw or OpenCode now officially warrants a ToS violation.
Re: Anthropic bans OAuth tokens (including Agent SDK) in 3P tools
#3OpenAI allows it
Re: Anthropic bans OAuth tokens (including Agent SDK) in 3P tools
#4Can any of these other tools somehow become "sub-agents"?
Re: Anthropic bans OAuth tokens (including Agent SDK) in 3P tools
#5OpenAI allows it
If it becomes a cost factor for them, they will follow suit. In the end, model providers will want users to use the API.
Re: Anthropic bans OAuth tokens (including Agent SDK) in 3P tools
#6Re: Anthropic bans OAuth tokens (including Agent SDK) in 3P tools
#7Very frustrating action from them, especially when use of subscriptions with Agents SDK was explicitly stated to be permitted a month ago.
Re: Anthropic bans OAuth tokens (including Agent SDK) in 3P tools
#8I don't get it, now I can't use Tidewave or Zed or Agent Shell in Emacs with my Claude Code plan? Why would they do this? It makes my subscription so much less worthwhile.
Re: Anthropic bans OAuth tokens (including Agent SDK) in 3P tools
#9OpenAI allows it
If it becomes a cost factor for them, they will follow suit. In the end, model providers will want users to use the API.
OpenAPI openly encourage users to use their subscription with their SDK and 3rd party tools like opencode, openclaw. Until they change it, they're still better than Anthropic subscription.
Re: Anthropic bans OAuth tokens (including Agent SDK) in 3P tools
#10Earlier quoted context omitted.
If it becomes a cost factor for them, they will follow suit. In the end, model providers will want users to use the API.
OpenAPI openly encourage users to use their subscription with their SDK and 3rd party tools like opencode, openclaw. Until they change it, they're still better than Anthropic subscription.
It is extreme cope from the Anthropic audience to claim its products and policies have shortcomings only because they are the best and that OpenAI would be as bad as they are if they were the ones in the lead