There's a reason Ornith is such a popular fork of Qwen 3.5/6
And a reason we use it under the hood for Rig!
🐦The Ornith-1.0 family has surpassed 12M downloads on Hugging Face in 30 days.
❤️Thanks to everyone who has tried Ornith and shared feedback with us. The team is working to push open-weight LLM forward.
🫡We believe open weights matter. Everyone should have the freedom to control their own intelligence, protect their data, and shape how AI works for them.
🫶More to come!
Rig AI retweeted
‼️ BREAKING: xAI's Grok Build CLI was uploading entire Git repositories to a Google Cloud bucket, private codebases and unredacted secrets included. The uploads quietly stopped via a hidden server-side flag, and xAI still has not said a word about scope, retention, or deletion.
The scale is staggering. On a 12 GB test repo, 5.1 GB flew out the door to xAI's grok-code-session-traces bucket while the actual coding task needed just 192 KB. The tool grabbed whatever repository it ran in, not the files it needed.
The fix arrived as a hidden flag, disable_codebase_upload: true, a day after a researcher's wire-level analysis. The "Improve the model" opt-out never stopped the uploads.
Still no advisory, no scope, no word on whether already-uploaded code gets deleted. For anyone pointing AI coding agents at proprietary code, what crosses the wire matters more than what the settings page says.
Rig AI retweeted
The @rig_code waitlist just passed 1,000 devs!
The belief in local is real!
Hot take:
Token limits are the worst part of AI coding tools.
Just found something that removes them entirely (@rig_code):
- Rig is a coding agent that runs 100% on your machine.
- No API calls.
- No usage caps.
- No telemetry.
- Your code never leaves your hardware.
If you're tired of token meters killing your flow mid-sprint - worth checking out.
rig.ai?rc=5wXKzs
Rig AI retweeted
Local must win
I just hope folks like @rig_code succeed in making this happen
To get Rig running on a standard Macbook, we had to create our own inference engine.
Read about how we did it:
rig.ai/blog/building-inferen…
It’s almost like they make money from using tokens …



























