Robbyant/lingbot-video

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

#AI video generation

Python

979

49

1 contributors

Apache License 2.0

FeaturedAdvertise to 180K+ monthly visitors

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Momentum

How fast Robbyant/lingbot-video is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 7 – Nov 5, 2026

Stars +36 in 60 days

4

Forks +2 in 60 days

1

Merged PRs 0 in 60 days

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 7Sep 15Sep 23Oct 1Oct 9Oct 17Oct 25Nov 2

Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day	Stars gained	Forks gained	Merged PRs
Mon, Sep 7, 2026	+1	+0	0
Tue, Sep 8, 2026	+3	+0	0
Wed, Sep 9, 2026	+1	+0	0
Thu, Sep 10, 2026	+1	+0	0
Fri, Sep 11, 2026	+0	+0	0
Sat, Sep 12, 2026	+0	+0	0
Sun, Sep 13, 2026	+1	+0	0
Mon, Sep 14, 2026	+1	+0	0
Tue, Sep 15, 2026	+3	+1	0
Wed, Sep 16, 2026	+1	+0	0
Thu, Sep 17, 2026	+1	+0	0
Fri, Sep 18, 2026	+2	+1	0
Sat, Sep 19, 2026	+1	+0	0
Sun, Sep 20, 2026	+0	+0	0
Mon, Sep 21, 2026	+2	+0	0
Tue, Sep 22, 2026	+0	+0	0
Wed, Sep 23, 2026	+0	+0	0
Thu, Sep 24, 2026	+0	+0	0
Fri, Sep 25, 2026	+0	+0	0
Sat, Sep 26, 2026	+0	+0	0
Sun, Sep 27, 2026	+1	+0	0
Mon, Sep 28, 2026	+0	+0	0
Tue, Sep 29, 2026	+0	+0	0
Wed, Sep 30, 2026	+1	+0	0
Thu, Oct 1, 2026	+0	+0	0
Fri, Oct 2, 2026	+0	+0	0
Sat, Oct 3, 2026	+0	+0	0
Sun, Oct 4, 2026	+0	+0	0
Mon, Oct 5, 2026	+0	+0	0
Tue, Oct 6, 2026	+0	+0	0
Wed, Oct 7, 2026	+0	+0	0
Thu, Oct 8, 2026	+2	+0	0
Fri, Oct 9, 2026	+0	+0	0
Sat, Oct 10, 2026	+2	+0	0
Sun, Oct 11, 2026	+1	+0	0
Mon, Oct 12, 2026	+0	+0	0
Tue, Oct 13, 2026	+1	+0	0
Wed, Oct 14, 2026	+4	+0	0
Thu, Oct 15, 2026	+0	+0	0
Fri, Oct 16, 2026	+0	+0	0
Sat, Oct 17, 2026	+0	+0	0
Sun, Oct 18, 2026	+0	+0	0
Mon, Oct 19, 2026	+0	+0	0
Tue, Oct 20, 2026	+0	+0	0
Wed, Oct 21, 2026	+2	+0	0
Thu, Oct 22, 2026	+1	+0	0
Fri, Oct 23, 2026	+0	+0	0
Sat, Oct 24, 2026	+0	+0	0
Sun, Oct 25, 2026	+0	+0	0
Mon, Oct 26, 2026	+1	+0	0
Tue, Oct 27, 2026	+0	+0	0
Wed, Oct 28, 2026	+0	+0	0
Thu, Oct 29, 2026	+0	+0	0
Fri, Oct 30, 2026	+1	+0	0
Sat, Oct 31, 2026	+0	+0	0
Sun, Nov 1, 2026	+0	+0	0
Mon, Nov 2, 2026	+0	+0	0
Tue, Nov 3, 2026	+0	+0	0
Wed, Nov 4, 2026	+0	+0	0
Thu, Nov 5, 2026	+1	+0	0
Total	+36	+2	0

#1 on the list
Rank that day
Not trending

Mentions and achievements

Where people are talking about Robbyant/lingbot-video, and every badge it has earned

Aug 201 post
- • Efficient MoE architecture with ~3x faster inference • Trained on 70,000+ hours of embodied data and massive web videos • Multi reward system for aesthetics, physical rationality, and task…
  Read full on X, posted by @the_osps
  @the_osps · x.com
28 days earlier
Jul 231 post
- Open video models are starting to aim at something more useful than prettier short clips. LingBot-Video is interesting because it treats video generation as structured world modeling: a 30B MoE…
  Read full on X, posted by @AlexshevPm
  @AlexshevPm · x.com
7 days earlier
Jul 162 posts
- My biggest takeaway has less to do with benchmark scores. The authors present LingBot Video as a foundation for embodied AI applications such as: • Synthetic data creation • Policy evaluation •…
  Read full on X, posted by @koloveski
  @koloveski · x.com
- Here's the framing that stuck with me most. The authors don't pitch this as a better text-to-video tool. They pitch it as infrastructure — something that can function as: → A synthetic data engine…
  Read full on X, posted by @ColawMide
  @ColawMide · x.com
Jul 141 post
- The benchmark result is strong too. 🔥 On RBench, LingBot-Video gets a 0.620 average score, the top average in the reported table. It does not win every column. Closed-source Wan 2.6 still leads some…
  Read full on X, posted by @EyeingAI
  @EyeingAI · x.com
Jul 132 posts
- LingBot-Video: An open-source MoE video foundation model for embodied AI
  Read full on Hacker News
  Hacker News
- Most video models learn mostly from internet video. This one learns from robots. LingBot-Video from @robbyant_brain is trained on 70,000+ hours of embodied footage on top of internet-scale video.…
  Read full on X, posted by @heyshrutimishra
  @heyshrutimishra · x.com
Jul 121 post
- The bigger framing from the authors: not a video generator, a robot-brain substrate. Data engine. Policy evaluator. Action planner. Tested via action-conditioned rollouts on datasets it never trained…
  Read full on X, posted by @HeyNayeem
  @HeyNayeem · x.com
Jul 112 posts
- The bigger idea is what makes this interesting. Instead of treating it as "just another video generator," the authors position it as something that could help with: ✔️ Synthetic robot data ✔️ Policy…
  Read full on X, posted by @HeyToha
  @HeyToha · x.com
- Most video models learn what the world looks like. Robotics needs models that learn what happens next. This is LingBot-Video from @robbyant_brain — the world’s first large-scale open-source…
  Read full on X, posted by @XRoboHub
  @XRoboHub · x.com