Hacker News Reader

Comment by languagehacker | Hacker News Reader

My OpenClaw assistant (who's been using Claude) lost all his personality over the last week, and couldn't figure out how to do things he never had any issues doing.

I racked up about $28 worth of usage and then it just stopped consuming anymore, so I don't know if there was some other issue, but it was persistent.

I got sick of it and used a migration script to move my assistant's history and personality to a claude code config. With the new remote exec stuff, I've got the old functionality back without needing to worry about how bleeding-edge and prone to failure OpenClaw is.

I feel like this is what their plan was all along -- put enough strain and friction on the hobbyist space that people are incentivized to move over to their proprietary solution. It's probably a safer choice anyway -- though I'm sure both are equally vibe-coded.

View on HN

I thought the reason OpenClaw was banned because of the strain it's putting on the systems.

(Well, 3rd party stuff was already illegal, and I believe remains so (sorta-kinda tolerated now? with the extra usage[0]) but enforcement seemed to be based on excessive usage of subs.)

Doing the same thing but with 50K of irrelevant, proprietary system prompt, doesn't seem to improve the situation!

i.e. my question here is: if you replicate OpenClaw with `claude -p prooompt` and cron, is Anthropic happy? (Or perhaps their hope is that the people able and willing to do that represent a rounding error, which is probably true.)

[0] https://news.ycombinator.com/item?id=47633568

Well when the middleman between you and your users is bought out by the competitor, it makes sense to move away from it. It's a bit like Apple selling iPhones in a Microsoft store.

What does your Claude Code implementation of OpenClaw look like?

Not who you asked but I slapped this together in 100 lines of code and you may find it useful. It's just `claude -p proompt` (or indeed, `codex exec prooompt` inside a Telegram bot. (Was annoyed by NanoClaw's claim that it was 500 lines, so tried my own hand at it ;)

No memory, no cron/heartbeat, context mgmt is just "new chat", but enough to get you started.

Note: no sandboxing etc, I run this as unprivileged linux user. So it can blow up its homedir, but not mine. Ideally, I'd run it on a separate machine. (My hottest take here is "give it root on a $3 VPS, reset if it blows up" ;)

https://github.com/a-n-d-a-i/ULTRON

You may also enjoy CLIProxyAPI, which does the same thing (claude -p / codex exec) but shoves a OpenAI compatible API around it. Note: this probably violates every AI company's ToS (since it turns the precious subsidized subscription tokens into a generic API). OpenAI seems to tolerate such violations, for now, because they care about good. Anthropic and Google do not.

(Though Anthropic may auto-detect and bill it as extra usage; see elsewhere in this thread. Situation is very confusing right now.)

https://github.com/router-for-me/CLIProxyAPI

I used https://github.com/Kevjade/migrate-openclaw, and then started running Claude Code with remote exec against an empty folder that I've advised it to start adding new memories into. So far, my bot's personality is back, and it can utilize the same skills as before, which is was failing on last week.

I don't have an especially heavyweight implementation, because I only use mine to review things I've written in my Apple Notes (journaling of various kinds, mostly) and give insights.

Reply on news.ycombinator.com