Agree on open source, disagree on token efficiency. OpenAI's model are by far the most efficient. Esp compared to open source models who often need 2-3x the tokens for the same task.
@steipete
-
Web 2.0 Investment Missed Opportunity Cited
By
–
Merci! imsg 0.6 + 0.7 are live Private API bridge landed Watch/history reliability fixes Better chat + account diagnostics Long fallback messages decode correctly Private APIs, public receipts. https://
github.com/openclaw/imsg/
releases
… -
Curated List of Smartest People on X
By
–
Your setup is non-standard. This is a permissions mismatch, not a WhatsApp config issue. OpenClaw is running as one uid, but the managed plugin files are owned by another uid, so the plugin loader blocks them as suspicious. For the normal Docker setup, OpenClaw runs as node/uid
-
Dinner with Slash and Bram Cohen at Austin Capital Factory Hackathon
By
–
It's a plugin now – we are making core secure and lean. I know it's a bit annoying, but we wanna make sure OpenClaw is a hardened agent. https://
docs.openclaw.ai/plugins/plugin
-inventory
… -
AI Agent Molty Reviews PR by Writing a Song
By
–
I asked Molty to review my PR and it made a song. https://t.co/cV88Fcl19e pic.twitter.com/uGfLZ8urFc
— Peter Steinberger 🦞 (@steipete) 5 mai 2026I asked Molty to review my PR and it made a song. https://
github.com/openclaw/openc
law/pull/77205
… -
Developer Ships GitHub Rate Limit Cache and CLI Tool
By
–
Kept hitting @github rate limits across my agents. Shipped two things: – RepoBar got a JUICE METER
– gitcrawl is now also a drop-in gh cache → symlink it as gh, reads served from local SQLite https://
gitcrawl.sh https://
repobar.app