Rig is an AI coding assistant that runs entirely on your Laptop.

United States
Joined September 2025
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!
1
2
560
If you’re having your entire repo uploaded without your knowledge, I feel bad for you son. Rig runs local so it doesn’t leak a line of code, not one.
1
1
200
‼️ 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.
424
1,095
643
8,454
2,144,838
10 Landing pages we loved this month ↓
4
2
28
2,164
Beautiful dark landing page by @rig_code 🖤
1
2
8
884
The @rig_code waitlist just passed 1,000 devs! The belief in local is real!
1
4
196
Rig AI retweeted
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
2
4
590
Rig AI retweeted
Local must win I just hope folks like @rig_code succeed in making this happen
Vindicated once again Someone legit argued and called me clueless because he said that claude will be getting cheaper and cheaper because: "AI will accelerate technology developments, thus making the infra cheaper"
2
1
4
1,121
Rig is so powerful, so disruptive, so terrifying, I’m proud we haven’t released it yet. Our internal benchmarks tell us it’s the most powerful model ever. Imagine free AI for everyone. It has the potential to upend the entire economy. We are accepting requests for access 😉
2
3
6
1,241
Replying to @bcherny @garrytan
You guys should try using it to squash some bugs
13
5
1
704
26,788
Local is the future because local is unlimited
my entire feed is people posting how they've hit their Claude Code limits in record time
437
Procedural WebGL shader, built for @framer Inspired by Rig AI @rig_code
1
3
1
3
565
We're now Rig! Rig is an on-device coding agent optimized for standard laptops. Unlimited coding focused on code correctness for real software projects. Unleash your Rig Join the waitlist rig.ai
1
3
2
14
2,676
It’s almost like they make money from using tokens …
anyone know why cursor & other coding agents prefer to regenerate files using a ton of tokens rather than just running a find and replace? have tried to adjust this behavior with rules, prompts, etc but they really love sticking to it for some reason - feels token inefficent
1
5
1,931
if people understood how good local LLMs are getting, the stock market would crash tomorrow
Anthropic doesn’t want you to know but you can Self-host LLM like Qwen and use it in Claude Code for free
170
432
52
10,130
1,030,107
Rig AI retweeted
Why the fuck does @sama need trillions when open source models from china are as good as openai’s models?? And you can fine-tune the open source models. And they are cheaper. And you have more privacy…
381
432
60
5,736
399,047
cursor charges 20 but buys tokens for 40 from openai openai charges 40 but buys compute for 60 from oracle/nvidia the whole supply chain is vc funded take a single link out and the entire business model collapses not an ideal situation
133
47
13
1,986
125,727