EN
Back to the archive

The archive · AI & Models · Product decision · 2025–2026

BettaFish: student's 10-day vibe-coded AI thesis tops GitHub, wins ¥30M

A BUPT senior vibe-coded BettaFish in 10 days; it hit #1 GitHub Trending and led to a ¥30M investment from Shanda founder Chen Tianqiao.

BettaFish (微舆) · MiroFish

The betOne person with AI tools can build a shippable multi-agent product in ten days; social-opinion analysis is the wedge, and the same engine can sell prediction next.Live

What the business is

BettaFish (微舆) is an open-source multi-agent public-opinion analysis system: it crawls 30+ Chinese and global social platforms, has specialist agents debate findings in a 'forum', and generates structured 30-page research reports from a chat prompt; a follow-up engine, MiroFish, builds simulated 'digital worlds' to predict how events unfold.

Starting capitalBootstrapped from under ¥10k of personal savings (Xinhua Finance (新华财经)); then Shanda Group committed ¥30M (≈US$4.2M) to incubate MiroFish after Chen Tianqiao (陈天桥) saw the demo in December 2025.

How it started

Summer 2025: Guo Hangjiang (郭航江, aka BaiFu), then a 22-year-old senior at Beijing University of Posts and Telecommunications, wanted to finish his thesis early to free time for an internship. He spent the last ten days of vacation vibe-coding BettaFish (微舆) with Claude Code and released it as an open-source project; a PhD-student mentor dismissed it as 'not a qualified thesis'.

What happened

BettaFish crawled to ~1k stars, so Guo wrote a farewell essay on Xiaohongshu titled 'What a 1k-star open-source project gives a student'; a week later tech influencers amplified it and stars jumped from 5k to 30k+ within days, putting the project at #1 on GitHub's global trending chart on 2025-11-03. Emails with internship, partnership and investment offers poured in, and Shanda's founder Chen Tianqiao personally recruited him. Guo moved to Shanghai, built MiroFish (a swarm-intelligence prediction engine) in another ten days, sent Chen a demo on 2025-12-16, and within 24 hours Chen committed ¥30M for deep incubation. MiroFish hit #1 on GitHub Trending on 2026-03-07.

How it ended up

Ongoing: Guo's startup, backed by Shanda's ¥30M, is incubating MiroFish; by March 2026 his team had grown to about ten people mixing AI-native indie developers and senior engineers, and BettaFish had ~42k GitHub stars by August 2026.

Background

BettaFish (微舆) is an open-source multi-agent public-opinion analysis system: crawlers pull millions of comments from 30+ social platforms, specialist agents with different tools argue findings through a 'forum' mechanism, and a report engine turns the debate into a structured, illustrated 30-page analysis from a single chat prompt. Founder Guo Hangjiang (郭航江, aka BaiFu) bet that one person directing AI could build a product that normally takes a team — and that opinion analysis was the wedge into a broader data business.

Guo, a 22-year-old senior at Beijing University of Posts and Telecommunications, built the first version in the last ten days of summer 2025 using Claude Code while trying to finish his thesis early for an internship; a PhD mentor dismissed it as 'not a qualified thesis'. The project crawled to 1,000 stars, so Guo wrote a Xiaohongshu farewell essay — a week later tech influencers amplified it, stars jumped from 5k to 30k+ within days, and BettaFish hit #1 on GitHub's global trending chart on 2025-11-03.

Shanda Group founder Chen Tianqiao (陈天桥) recruited Guo to Shanghai, where he built MiroFish — a swarm-intelligence engine that simulates thousands of agents in a 'digital world' to predict outcomes — in another ten days. Chen committed ¥30M within 24 hours of seeing the demo (December 2025). MiroFish hit #1 on GitHub Trending on 2026-03-07; as of August 2026 BettaFish had ~42k stars and Guo's team had grown to about ten people.

What has to be true

  • Vibe coding compressed a multi-agent product that normally takes a team months into ten days, making a solo student's thesis competitive with funded startups.
  • The product answered a real, repeated need — enterprises pay teams to produce opinion analysis — instead of being a demo with no buyer.
  • The virality had a repeatable trigger: a milestone essay that tech influencers amplified pushed stars past GitHub's trending threshold, and the second project re-ran the same play.
  • A single user complaint ('so what do I do with the report?') redirected the roadmap from analysis to prediction — which is what the investor actually funded.
  • Shanda paid for the person and the pipeline, not the product: Chen said the tech wasn't outstanding, but the ability to define real problems and ship fast was.

What can be applied

Vibe coding collapses shipping cost, so the scarce skills become defining a real problem and directing AI; the durable bet is turning GitHub stars into paying users.

Aftermath

As of 2026-09-02, Guo's startup operates under Shanda's umbrella, incubating MiroFish with the ¥30M commitment; by March 2026 both projects sat in GitHub's trending top 5 together, and BettaFish had ~42k stars with ~7.6k forks by August. The company is pushing MiroFish toward monetizable decision-support use cases such as financial-market prediction and hot-event simulation, while BettaFish keeps shipping daily iterations in response to community feedback. Whether the bet pays off now depends on converting open-source attention into paid product revenue.

Sources

spotted an error? The archive wants to know.

Your turn

You just read one. Describe what you are building, and see who is betting on the same thing.

Free account · 3 free questions · no card

Related cases