Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

> for third-party harnesses

What's the exact definition of third-party harnesses? They have an Agent SDK in Claude Code that can be used. Are they trying to say that only Anthropic products can use pro/max plans?

Some of the vigorous defending of Claude changing the deal, makes me wonder if Open Claw is banned because they have their own version they are working on deploying.

This is the classic car wash subscription scheme. You sign up a bunch of people for $40 a month to wash their car. Most people only go to wash their car once or twice a month (or even less), which offsets those few folks that do it three times a week or more.

The problem Anthropic is running into is that OpenClaw made it easy for everyone to become one of those folks that washes their car three times a week or more.

I’m sure they were losing money on subscriptions in general but now they are really losing money. Shutting off OpenClaw specifically probably helps stem some of the bleeding.

What about when you use Claude agent SDK on your laptop?

Extra usage is very sneaky you don't get any notice that you are using extra usage and could end up with unnecessary costs in case you would have preferred to wait an hour or so.

OpenAI / Gpt should do the opposite. Let the people use their subscription on openclaw and break down which tasks are efficient vs inefficient. Help openclaw learn to be efficient.

Their ultimate goal is to do everything. Eventually, if people are using their service for a specific use case, it's highly likely they will just step in and do it themselves

This seems like a reasonable move even putting aside the reasoning about breaking the assumptions that make a subscription model cheaper than a pay-per-use model.

Why would they actively subsidize the ticking timebomb? When OpenClaw has an especially large security incident, Anthropic will probably be affected just for the association.

Like, right alongside this post on the front page, we have a post about a relatively serious privilege escalation vulnerability in OpenClaw.

Skimming the comments it feels like devs are giving Anthropic way too easy of a pass. Killing access to Openclaw is whatever. But Anthropic is proving to be not worth our trust or our data. They actively talk about replacing developers and act in so many ways against their own customers.

Discussion (655 points, 1 month ago, 793 comments) https://news.ycombinator.com/item?id=47069299

Super confusing email. Not sure why I received. Am i to assume my account was flagged? I only use my subscription for Claude Code.

UPDATE:

reply on x Thariq @trq212 only flagged accounts, but you can still claim the credit

It's the tragedy of the commons where OpenClaw users abuse the system and everyone has to suffer.

Anthropic is a great showing for startup founders how if you have a great product people will buy it, even if they dislike your pricing, your marketing and the CEO opinions.

Real PMF sells itself. The risk is of course the competition catching up, I bet switching costs are very low on this setup.

The main reason I find myself using Opus is because it's a better communicator. (Yes, I know it's better in some areas like frontend vs. others but this is not significant enough for my purposes.)

So this change has actually forced a reckoning of sorts. Maybe the best option is to outsource the thinking to another model, and then send it back to Opus to package up.

Ironically this is how the non-agent works too to an extent.

How does Anthropic detect that a person is using OpenClaw vs using Claude Code?

Forgive me if someone asked this already and I can't find it in the comments.

Go pay for the API. It's not complicated.

Is this going to nuke all bring your own API 3rd party tools? I've been casually using fewshell https://github.com/few-sh/fewshell with my Claude api key, I really hope it's going to keep working. I've just finally managed to turn myself into a reasonable devops team with it.

Hoping this means that we'll see a lot of barely used Mac Minis for sale from the people who were bragging about buying them.

I've been running multiple OpenClaw agents 24/7 since January. While I saw this coming, it was still a kick in the teeth. I've been iterating through workarounds and potential solutions. My OpenClaw gateway costs are estimating roughly 7x what I pay for Max today.

https://focusoverfeatures.substack.com/p/claude-max-blocks-o...

Just use codex. A company that has not released any open weights models and goes after banning accounts and suing companies is not really the kind of company I want to give my money too. And gpt5.4 is the best model out there. Some people overthink on personality but I just want good code.

I'm honestly completely in favor of this. Anthropic obviously budgets their capacity based on projected human usage patterns coming through their native app suite (Claude Cowork, Claude Code, etc.). They should not be expected to shoulder the burden of community tools like OpenClaw that are effectively designed to strategically max out usage windows on the plan. That has clearly caused issues with uptime in the past couple of months and I've gotten pretty fed up with the degraded service quality while I'm just trying to use Claude Code as it's intended to be used. I'm happy to see they're doing something about this. Seems like a totally fair move to me. I'd rather that Claude Code functions well when I'm using it according to its design.

I think its not good idea , they are constraining the usage of other platforms such as openclaw.These restriction methods will not be positive point to anthropic.

As the demand for GPUs grows and supply cannot match it, the GPUs are going towards the enterprise and it'll be the haves vs the have-nots.

Instead of not driving to work to save fuel, frugal companies are going to have their engineers work on weekends to save tokens.

We built an open-source orchestrator that routes across providers with direct API keys. If you're looking for alternatives to subscription-locked tools: https://modelreins.com

Based on this and recent product releases, Anthropic seems keen on building a closed ecosystem around their excellent model. That is their business choice, I suspect it will work well. But I cannot say I am particularly excited to have my entire development stack owned by one company.

Anthropic measures your usage based on token consumption

We are paying for a certain amount of token consumption

Why then, is this an outsized strain on your system Anthropic?

It's like buying gasoline from Shell, and then Shell's terms of services forcing you to use that gas in a Hummer that does 5 MPG, while everyone else wants to drive any other vehicle.

Anthropic might underestimate how many users got a subscription because of openclaw and the likes. I did; $100 max subscription. Not renewing it. GLM and minimax are viable alternatives for a fraction of the cost.

This is what I mean when I say what LLMs as a technology are not empowering to humans.

They become how you think, then company has you: hook line and sinker

Claude usage limits are insane. I love their models but had to cancel my personal plan because I would burn through my weekly limits in 2 days. I use them for work but I spend like $30-50 __per day__. Not something I'd pay for myself.

If OpenClaw is just "claude -p", then how do they know when you're using OpenClaw?

I believe the capacity about 30%. They did just spend the entire last month of feature releases in Clade Code replacing "claw" features.

So, to me its a "we built it into our world use ours"

Edit: FWIW I am an avid hater of all claw things, they're security nightmare.

I got fed up with Claude code limits and have been using a combination of qwen3-coder, gemma4, and qwen3-vl locally. Gets me 90% of the way there and CC is still around for now if I need it.

Btw even at insane markups $200/mo means GPUs break even pretty fast.

And so it begins...

I guess they're only sending this to people who use tools like OpenClaw. I don't, and haven't gotten an email. And I guess also won't get the free extra usage credit offer. Ah well.

Claude is a great model. But anthropic’s user hostile practices have forced me to terminate my sub with them. Right now I am all in on GitHub copilot and that’s primarily how I get my opus tokens.

Given the sheer amount of logging that happens in Claude Code based on the leak, I'm not surprised. This isn't about load, this is merely about cost.

Claude Code is subsidized because of data collection.

It seems like they are suffering from compute problems bcs they are not only allowing OpenClaw but also limiting the chats

This is exactly why building daily workflows on top of proprietary API wrappers is a ticking time bomb. The moment your tooling becomes an outsized strain, they just flip the switch on you.

This email gives out the endgame - eventually, Claude subscription would be ~30% cheaper than API costs.

Our engineering team averages 1.5k per dev per month on credit costs, without busting Max limits today.

Oh that is the crux of it, I was wondering why they are leading with the free credit in their email and what the catch is. I guess for someone that doesn’t use openclaw it doesn’t matter.

I get why they block OpenClaw and it makes sense but I wonder if they can actually detect OpenClaw calling Claude Code CLI using something like acpx.

It's simply identical to how people use Claude Code locally.

Why do this, the subscription has usage limits so its controlled that way, who cares what you use it for?

I always thought this was the case since they declared war against Opencode and its users.

The lines drawn by their consumer vs commercial TOS was clear and I never subscribed because of it.

I think this is why the LLM era will not produce as much automation as people think.

We have had the ability to automate browser activities for a long time—but, online service providers don’t want to be behind a layer of automation, which is why captchas were invented.

Automating things on the Internet has never been a technology obstacle, it has been a social one.

I don’t see how anything has changed!

In fact I recently received an updated ToS from eBay saying I am not allowed to use an AI agent to buy stuff on their site. Just a matter of time until others follow suit!

Edit: I misunderstood what was happening. Thanks to the comment below for clarifying.

They also forced OpenCode to remove support as well. Thankfully there is always self hosting and a shit ton of competitors that let you use whatever local software you want.

Does this mean I can't use `claude -p` in bash scripts now?

Less than 24hr notice on a Friday: either Anthropic is dropping S tier next week or they massively fumbled over the past 2 months in self owns and outages.

For anyone interested, I’m cleaning up a project I’ve been working on that is a router for arbitrary agents derivative of/forked from ZeroClaw… part of what it does is let you switch between different agents on WhatsApp/Signal/Matrix etc via !switch commands, so that part isn’t an agent itself but just wants to own your channels so you can have any number of agents talking to the same handful of channels without contention.

I do also bundle a default agent with it, also forked from ZeroClaw, with a goal of being more or less prompt injection proof and hopefully able to centralize some configuration and permissions for most or all of the agents it manages, though that part is very rough sketch/plan at the moment I’d love feedback and help on from anyone interested…. Two projects, clash and nono caught my eye in this space, I think both leverage Linux landgrant but I may also use landrun for similar control of other processes like openclaw that it may manage for the user, still figuring out how and where to fit all the pieces together and what’s pragmatic/what’s overkill/what overlaps or duplicates across various strategies and tools. Right now there’s real bash wrappers that evaluate starlark policies, hoping to fully validate better end to end but if you’re interested a few others users testing, validating and/or contributing Claude tokens to the project could be invaluable at this stage. Plan to open source ASAP, maybe tonight or tomorrow if there’s interest and I have time to finish cleanup and rename (I was calling it PolyClaw but that confuses with some weird polymarket Claude skill, so now the router is going to be ZeroClawed and the agent will stay NonZeroClaw in homage to ZeroClaw who it’s forked from… we may also integrate the new Claw Code port which is also rust, just for good measure/as a native coding agent in addition to the native claw agent )

Anyway the main reason I mention is it already has a working ACP integration for any code agent, and working now on using Claude codes native channel integration to make it appear as a full fledged channel of its own, as it now more or less does already to OpenClaw, for anyone wanting to gradually migrate away from their existing OpenClaw installation using this, towards Claude or some other agent. Email me or respond here if interested, or I’ll try and post link here once it’s fully public/open source

So is Codex the only SOTA that welcomes third-party harness?