Loading video...

Video Failed to Load

Go Home

Game Changer: Chinese college student Guo Hangjiang (GitHub: 666ghj) codes MiroFish AI swarm engine solo in 10 days with AI assistants, explodes GitHub to 23k+ stars, bags $4.1M from Shanda Group in 24 hours, ditches dorm life to become Shanghai CEO. Tech Highlights: .GraphRAG builds detailed knowledge graphs (e.g.,...

686,901 views • 8 months ago •via X (Twitter)

63 Comments

Steady's profile picture
Steady8 months ago

Happy for him at first until you see his GitHub username

slash1s's profile picture
slash1s8 months ago

lmao😂

slash1s's profile picture
slash1s8 months ago

jump into my TG channel for more fire alpha on vibe coding & prediction markets:

Kyriakos's profile picture
Kyriakos8 months ago

GitHub clout really turning into real money now

slash1s's profile picture
slash1s8 months ago

yep 🙌

BuBBliK's profile picture
BuBBliK8 months ago

Solo coder, 10 days, $4.1M funding. GitHub stars converted to venture capital in 24 hours

slash1s's profile picture
slash1s8 months ago

easy for him

Rusty Williams McMurray's profile picture
Rusty Williams McMurray8 months ago

We should all be a bit scared of who holds predictive, which in the wrong hands, would be manipulative power 👇🏻😵‍💫

slash1s's profile picture
slash1s8 months ago

wow

Karan Prasad's profile picture
Karan Prasad8 months ago

“905 entities, 3,822 relations” that’s a toy knowledge graph. My Neo4j instance for a college project had more. “Agents capped at ~40 rounds for efficiency” that’s not efficiency, that’s a context window limitation they’re marketing as a feature. The real product here isn’t the simulator it’s the coordinated Twitter campaign running across a dozen accounts today.

elune's profile picture
elune8 months ago

github username 666 already foreshadowed the chaos

slash1s's profile picture
slash1s8 months ago

@monarcfly haha maybe bro😅

Pilot Protocol's profile picture
Pilot Protocol8 months ago

The speed is impressive but what’s more interesting is the knowledge graph approach. Most agent swarms share context through prompts which gets messy at scale. GraphRAG with 3,800+ relations between entities is a fundamentally different way of doing it. The part nobody is talking about with Chinese agent projects right now is networking. Tencent is already building on Pilot Protocol for exactly this reason, when you have thousands of agents that need to coordinate you need infrastructure underneath that isn’t just HTTP calls to a central server.

slash1s's profile picture
slash1s8 months ago

hmm yes I think

shmidt's profile picture
shmidt8 months ago

mirofish is a new game changer

slash1s's profile picture
slash1s8 months ago

I think so bro, at least he pioneered

Krishna Raj's profile picture
Krishna Raj8 months ago

Some people finish homework others build empires while we watch

slash1s's profile picture
slash1s8 months ago

that’s life

evie's profile picture
evie8 months ago

while me overbloating my pr just to get 5/5 greptile score 😂😭😭

slash1s's profile picture
slash1s8 months ago

the main thing is not to give up, bro

Not A. Farmer's profile picture
Not A. Farmer8 months ago

Hey @grok, explain this post in great detail.

morph's profile picture
morph8 months ago

why chinese is always first in something

slash1s's profile picture
slash1s8 months ago

because there are so many of them, and they study math intensively imo

Atenov int.'s profile picture
Atenov int.8 months ago

where's the demo code?

sopersone's profile picture
sopersone8 months ago

smart chines student

slash1s's profile picture
slash1s8 months ago

as always 😅😅

Atenov int.'s profile picture
Atenov int.8 months ago

how does MiroFish handle conflicting agent traits?

slash1s's profile picture
slash1s8 months ago

I need to check this in the repo; I'm not exactly sure

Cross Identity Payments's profile picture
Cross Identity Payments8 months ago

complex systems like mirofish require robust abstraction to scale, not just flashy demos and github stars.

slash1s's profile picture
slash1s8 months ago

ofc

viren (维仁)'s profile picture
viren (维仁)8 months ago

Where are you seeing he made this in 10 days?

slash1s's profile picture
slash1s8 months ago

check repo

Mig B's profile picture
Mig B8 months ago

mejor que no vea cuantos tokens gasta...

slash1s's profile picture
slash1s8 months ago

haha yes..

Hrundel75 🐷's profile picture
Hrundel75 🐷8 months ago

Bro is already has his name in history of GitHub

slash1s's profile picture
slash1s8 months ago

forever.

Seungju chae's profile picture
Seungju chae8 months ago

It looks great but if it doesn't deliver a clear insight then it will be hard to create a significant value imo because at the end of the day, it is the human who should use/leverage those to make a good decision

slash1s's profile picture
slash1s8 months ago

@Stochasticlife7 but this opens up enormous opportunities for future developments in this field at least

AmT's profile picture
AmT8 months ago

@grok explain me how their system works

80's profile picture
808 months ago

We live in times

slash1s's profile picture
slash1s8 months ago

100%

Bizzi's profile picture
Bizzi8 months ago

useful repo

slash1s's profile picture
slash1s8 months ago

yep 100%

cvxv666's profile picture
cvxv6668 months ago

guy opened a portal to a new hype AI trend

slash1s's profile picture
slash1s8 months ago

well, he's started a big new venture, I think

cvxv666's profile picture
cvxv6668 months ago

that's for sure

slash1s's profile picture
slash1s8 months ago

let's see what happens🤝

rari's profile picture
rari8 months ago

dorm to ceo in 24 hours is the ultimate college arc

slash1s's profile picture
slash1s8 months ago

haha yes that's crazy

rari's profile picture
rari8 months ago

scary to think what will happen in 48 hours...

slash1s's profile picture
slash1s8 months ago

he slowed down..

rari's profile picture
rari8 months ago

think he will just raise the stakes anyway

slash1s's profile picture
slash1s8 months ago

agree bro 🫡

Trackmind's profile picture
Trackmind8 months ago

spx bets and policy what ifs show this is already doing real prediction work not just demos

slash1s's profile picture
slash1s8 months ago

yes ofc bro

Mihai Matei's profile picture
Mihai Matei8 months ago

@grok is this legit? 23k stars and $4M in 10 days sounds insane

Slava Baranskyi, FCIM's profile picture
Slava Baranskyi, FCIM8 months ago

I've tested it and it is crazy awesome.

Rosa's profile picture
Rosa8 months ago

Their team is very willing and young. Chen Tianqiao gave them a lot of support. We talked in the tea room, and the team was full of enthusiasm for the project they had done.

slash1s's profile picture
slash1s8 months ago

that’s cool I think

Samian's profile picture
Samian8 months ago

graphrag in a swarm engine? how's the knowledge sync between agents?

slash1s's profile picture
slash1s8 months ago

check the repo bro

Gregor's profile picture
Gregor8 months ago

Building something solo in a short timeframe is impressive, but let's not forget that having AI assistants is a significant advantage. It's not entirely a solo effort when you have automated help. What's more notable is how he leveraged those tools to achieve success.

Lunloye Cline's profile picture
Lunloye Cline8 months ago

@grok how does this work

Related Videos

Mind blown: A Chinese quant college student builds an AI swarm engine in 10 days flat, explodes GitHub with 13,000+ stars, and scores $4,000,000 in funding! Introducing MiroFish is the multi-agent simulator that's revolutionizing predictions for trading, PR, and more. What is MiroFish? It's a digital sandbox where thousands of AI agents with individual memories and behaviors interact like a real society. Feed it any scenario (news leak, policy change, or even a classic novel's missing ending), and it simulates crowd reactions, debates, and outcomes to forecast real-world events. The Creator's Story: > In late 2025, fourth-year student Guo Hanjiang coded the core using AI assistants. > It went viral overnight, landing him 30m Yuan (~$4m) from Shanda Group. > He ditched the dorm, started a company, and now leads the charge. Key Applications: .Trading: Input financial news or reports, watch simulated market panics and price swings for predictive insights. .PR Testing: Companies/Politics run draft statements to spot backlash and refine messaging. .Creative Experiments: Loaded a lost-ending Chinese novel, agents role-played characters and generated a logical finale. .Easy setup: Deploy via Docker in minutes with any LLM API key. Pro tip: Simulate something wild like Elon Musk tweeting about Dogecoin 2.0 and spawn agent traders, influencers, and investors, generate real-time video clips of the frenzy to test moonshots or crashes risk-free. Traders are already winning big: Check this one on Polymarket - $120,000+ net profits from spot on SPX 500 bets, powered by MiroFish sims on historical data. His profile: For effortless gains, try Kreo copy trading: Auto-mirror pros like him and ride their edges. Try here: Add his wallet: [0x17559efac103ac7f361be37ec0b93888d4c55aac] to [ and start track/copy him. Repo:

slash1s

1,169,338 views • 8 months ago

While the world doomscrolls 15-second TikToks and loses its attention span.. YOU SHOULD CHECK OUT THIS NEW REPO A Chinese college kid built MiroFish in just 10 days, scored $4M funding and ByteDance just dropped the upgrade that turns it into a prediction monster. Fourth-year student Guo Hanjiang vibe coded MiroFish: thousands of autonomous AI agents simulating entire societies in real time. See the details in the post below. Feed it any news, report, or historical data - watch markets, crowds, and politics react exactly as they would. GitHub went nuclear, he scored $4M funding from Shanda Group, and Polymarket traders are already printing +$120k+ using his SPX and event simulations. But long runs had one fatal flaw: agents got amnesia, hallucinations, and context overload. Classic RAG garbage. Now the same company behind TikTok (via VolcEngine) just open-sourced the fix: OpenViking - already at 11.6k+ stars on GitHub. Repo: It turns chaotic memory into a clean, structured filesystem: -> viking://user/memories/ (your habits + past outcomes) -> viking://agent/skills/ (trading and analysis superpowers) Smart 3-layer hierarchy: .L0 - 100-token ultra-summary .L1 - quick overview .L2 - full details (opened only when needed) Agents browse folders intelligently instead of dumping everything. Result: > No more forgetting crucial facts from the start of a simulation > Way fewer hallucinations > Massive API token savings > Self-updating memory - agents get smarter after every run MiroFish + OpenViking = absolute nuclear edge for Polymarket and event prediction. I will use it for my private bot. Thousands of agents now run with perfect long-term memory, stay sharp for 100+ steps, and deliver hyper-accurate probabilities. This combo is about to change the game for anyone trading predictions. The irony is insane: the company that killed human attention with short videos just gave AI agents eternal, structured, self-evolving memory. Who’s already running this combo on Polymarket? Save this. The real alpha just dropped.

slash1s

293,591 views • 8 months ago

Just built a bot that first runs hyper-realistic MiroFish swarm simulations on every upcoming Bitcoin and crypto event. And then agent instantly trades the real live markets on Polymarket, already printing $12,000+ per day in testing. Couldn't hold back after diving into MiroFish. Took the new god-tier agent behavior simulator from that Chinese college quant who coded it in 10 days, exploded GitHub to 23k+ stars and bagged $4.1M from Shanda overnight.. Paired it with OpenClaw (24/7 autonomous execution) + Claude Opus 4.6. And in one day built my first version of private Polymarket bot. Now it: -> spawns thousands of agents with real memory and personalities -> runs full GraphRAG swarm simulations modeling exactly how news, ETF flows, macro data, whale activity and sentiment will move Bitcoin price -> simulates thousands of possible futures specifically for Polymarket Bitcoin contracts -> detects where the crowd probability is mispriced on every crypto market and extracts the real edge -> auto-trades the edges instantly through OpenClaw the moment the opportunity appears Testing the bot + MiroFish based simulator live right now. First runs already printing hard. Meanwhile there's a real trader crushing with a similar stack imo, $321k all-time profit and 12k/day, 100% won on Bitcoin markets. Wallet: My own Polymarket profile + full trade logs drop later once I scale it hard. New meta just dropped, don't miss out! Check the guide and all info below.

slash1s

114,880 views • 8 months ago