RetroChainer (@RetroChainer) header
RetroChainer (@RetroChainer) profile picture

AI engineer · AI agents · Automations. @CELE8EX

Joined March 2025
RetroChainer retweeted
THESE 6 FREE REPOS SHOULD HONESTLY BE ILLEGAL. BLOOMBERG SPENT ~$2.67M TRAINING ITS OWN FINANCE AI. ONE OF THESE TRAINED ON A SINGLE GAMING GPU FOR $17.25. they're openbb, kronos, yfinance, fingpt, ta-lib and rea. 585k github stars between them. here's how it works: > yfinance and openbb pull the data > kronos reads the candles, fingpt reads the news, ta-lib runs the indicators > a bull and a bear argue, and the pm makes one call a day on aapl here's how to run it: 1 → pip install yfinance openbb 2 → python desk. py --ticker AAPL --data yfinance 3 → read the model votes before the pm decides honestly the fingpt row in its readme is the part i keep rereading. 1 × rtx 3090, 17.25 hours. the pm's last call is on screen in the clip. i won't say anything more. bookmark this ↓
if you want to build an AI trading system from scratch, start with this article you will end up with real market data, real backtests and a bot that trades for you 24/7
7
4
46
1,591
THESE 6 FREE REPOS SHOULD HONESTLY BE ILLEGAL. BLOOMBERG SPENT ~$2.67M TRAINING ITS OWN FINANCE AI. ONE OF THESE TRAINED ON A SINGLE GAMING GPU FOR $17.25. they're openbb, kronos, yfinance, fingpt, ta-lib and rea. 585k github stars between them. here's how it works: > yfinance and openbb pull the data > kronos reads the candles, fingpt reads the news, ta-lib runs the indicators > a bull and a bear argue, and the pm makes one call a day on aapl here's how to run it: 1 → pip install yfinance openbb 2 → python desk. py --ticker AAPL --data yfinance 3 → read the model votes before the pm decides honestly the fingpt row in its readme is the part i keep rereading. 1 × rtx 3090, 17.25 hours. the pm's last call is on screen in the clip. i won't say anything more. bookmark this ↓
if you want to build an AI trading system from scratch, start with this article you will end up with real market data, real backtests and a bot that trades for you 24/7
7
4
46
1,591
RetroChainer retweeted
THESE 6 FREE REPOS SHOULD HONESTLY BE ILLEGAL. 600K GITHUB STARS, $0, AND ONE BITCOIN BOT WHERE 4 SIGNALS VOTE LONG OR SHORT EVERY 5 MINUTES. they're freqtrade, ccxt, hummingbot, nautilus_trader, vn. py and rea. all open source. here's how it works: > rea maps an exchange app's order flow into 4 signals: trend, momentum, volume, taker flow > they vote long or short, the strategy sizes it, risk checks it > freqtrade executes on btc here's how to run it: 1 → pip install freqtrade 2 → freqtrade trade --strategy ReaFlow 3 → watch the 4 votes before it executes honestly the long % line is the part i keep watching. 95% at 09:15, 67% an hour later. the last call is on screen in the clip. i won't say anything more. bookmark this ↓
these 10 GitHub repos are the most DANGEROUS thing in trading right now together they give you a full AI hedge fund: a research desk, an investment committee and an execution desk in this article I've shown EXACTLY how to build it from scratch
9
8
100
6,355
THESE 6 FREE REPOS SHOULD HONESTLY BE ILLEGAL. 600K GITHUB STARS, $0, AND ONE BITCOIN BOT WHERE 4 SIGNALS VOTE LONG OR SHORT EVERY 5 MINUTES. they're freqtrade, ccxt, hummingbot, nautilus_trader, vn. py and rea. all open source. here's how it works: > rea maps an exchange app's order flow into 4 signals: trend, momentum, volume, taker flow > they vote long or short, the strategy sizes it, risk checks it > freqtrade executes on btc here's how to run it: 1 → pip install freqtrade 2 → freqtrade trade --strategy ReaFlow 3 → watch the 4 votes before it executes honestly the long % line is the part i keep watching. 95% at 09:15, 67% an hour later. the last call is on screen in the clip. i won't say anything more. bookmark this ↓
these 10 GitHub repos are the most DANGEROUS thing in trading right now together they give you a full AI hedge fund: a research desk, an investment committee and an execution desk in this article I've shown EXACTLY how to build it from scratch
9
8
100
6,355
THESE 6 FREE REPOS SHOULD HONESTLY BE ILLEGAL. A QUANT RESEARCHER COSTS A FUND ~$200K A YEAR. THIS DESK HAS 4 ANALYSTS, A BULL, A BEAR AND A PM, AND IT COSTS $0. they're tradingagents, ai-hedge-fund, vibe-trading, qlib, finrl and rea. 685k github stars between them. here's how it works: > rea maps the app's signal to 4 analysts: technical, sentiment, news, fundamentals > a bull and a bear argue, a trader proposes, risk checks it > the pm makes one call a day on nvda here's how to run it: 1 → pick one desk to start, not all six 2 → tradingagents --ticker NVDA --analysts all 3 → read the analyst votes before the pm decides honestly the vote heatmap is the part i keep watching. 90 sessions, one row per analyst. the pm's last call is on screen in the clip. i won't say anything more. bookmark this ↓
these 10 GitHub repos are the most DANGEROUS thing in trading right now together they give you a full AI hedge fund: a research desk, an investment committee and an execution desk in this article I've shown EXACTLY how to build it from scratch
15
11
1
120
6,189
RetroChainer retweeted
THIS FREE REPO SHOULD HONESTLY BE ILLEGAL. YOU TYPE ONE SENTENCE, "MAKE A MARKET ON BTC-USDT", AND A $0 AGENT STARTS BUYING AND SELLING BITCOIN ON BOTH SIDES OF THE BOOK. it's called vibe-trading. 36.8k stars, MIT, one command. here's how it works: > it picks its market-making skill and quotes 0.12% above and below the price > it keeps its inventory between 40 and 60%, so it never leans too far one way > then it sweeps every spread over the last 23 hours to find a better one here's how to run it: 1 → pip install vibe-trading-ai 2 → vibe-trading run -p "make a market on BTC-USDT" 3 → let it requote and watch the fills honestly the sweep is the part i keep watching. one square on it says +$16.85. which square is on screen in the clip. i won't say anything more. bookmark this ↓
if you want to build an AI trading system from scratch, start with this article you will end up with real market data, real backtests and a bot that trades for you 24/7
6
13
1
130
8,235
THIS FREE REPO SHOULD HONESTLY BE ILLEGAL. YOU TYPE ONE SENTENCE, "MAKE A MARKET ON BTC-USDT", AND A $0 AGENT STARTS BUYING AND SELLING BITCOIN ON BOTH SIDES OF THE BOOK. it's called vibe-trading. 36.8k stars, MIT, one command. here's how it works: > it picks its market-making skill and quotes 0.12% above and below the price > it keeps its inventory between 40 and 60%, so it never leans too far one way > then it sweeps every spread over the last 23 hours to find a better one here's how to run it: 1 → pip install vibe-trading-ai 2 → vibe-trading run -p "make a market on BTC-USDT" 3 → let it requote and watch the fills honestly the sweep is the part i keep watching. one square on it says +$16.85. which square is on screen in the clip. i won't say anything more. bookmark this ↓
if you want to build an AI trading system from scratch, start with this article you will end up with real market data, real backtests and a bot that trades for you 24/7
6
13
1
130
8,235
RetroChainer retweeted
QUANTCONNECT CHARGES INSTITUTIONS FROM $4,800 JUST TO ONBOARD. THE ENGINE UNDER IT IS FREE ON GITHUB, AND IN THIS CLIP IT SWEEPS 559 SETTINGS ON A YEAR OF QQQ. this is lean, the open-source engine behind quantconnect. 22k stars, apache-2.0, c# and python. → one rule: hold qqq while its 20-day return is above zero → the optimizer sweeps fast and slow windows, 559 pairs → peak sharpe 1.06, at 4 and 110 → 30 orders, and on oct 19 it sold and stepped aside honestly my favourite part is the volume profile. a year of qqq stacked up like a city. i kept the boring job for myself: reading the optimizer. where it sits right now is on screen in the clip.
Finally... AI trading system that I trust with my money Built on Jane Street’s rules, the firm behind ~10% of US stocks 6 GrokBot + Opus 5.5 agents find, test and kill trades 24/7 while you sleep In this article, I show you how to build it:
5
3
55
2,246
QUANTCONNECT CHARGES INSTITUTIONS FROM $4,800 JUST TO ONBOARD. THE ENGINE UNDER IT IS FREE ON GITHUB, AND IN THIS CLIP IT SWEEPS 559 SETTINGS ON A YEAR OF QQQ. this is lean, the open-source engine behind quantconnect. 22k stars, apache-2.0, c# and python. → one rule: hold qqq while its 20-day return is above zero → the optimizer sweeps fast and slow windows, 559 pairs → peak sharpe 1.06, at 4 and 110 → 30 orders, and on oct 19 it sold and stepped aside honestly my favourite part is the volume profile. a year of qqq stacked up like a city. i kept the boring job for myself: reading the optimizer. where it sits right now is on screen in the clip.
Finally... AI trading system that I trust with my money Built on Jane Street’s rules, the firm behind ~10% of US stocks 6 GrokBot + Opus 5.5 agents find, test and kill trades 24/7 while you sleep In this article, I show you how to build it:
5
3
55
2,246
RetroChainer retweeted
This is f*cking gold.. $10,000 ON TSLA. 11 ROLES ARGUED BEFORE EVERY TRADE, AND MY DESK FINISHED $1,530 AHEAD OF EVERYONE WHO JUST HELD. this is tradingagents. 115k stars, apache-2.0, a whole trading desk in one terminal. → 4 analysts: technical, sentiment, news, fundamentals → a bull and a bear argue it out → a trader, then 3 risk voices: aggressive, neutral, safe → the pm signs off or nothing happens honestly my favourite line is the vote bar. bull 67%, bear 33%, decision buy. i kept the boring job for myself: being the pm. the whole debate is on screen in the clip.
if you want to build an AI trading system from scratch, start with this article you will end up with real market data, real backtests and a bot that trades for you 24/7
9
6
66
4,205
This is f*cking gold.. $10,000 ON TSLA. 11 ROLES ARGUED BEFORE EVERY TRADE, AND MY DESK FINISHED $1,530 AHEAD OF EVERYONE WHO JUST HELD. this is tradingagents. 115k stars, apache-2.0, a whole trading desk in one terminal. → 4 analysts: technical, sentiment, news, fundamentals → a bull and a bear argue it out → a trader, then 3 risk voices: aggressive, neutral, safe → the pm signs off or nothing happens honestly my favourite line is the vote bar. bull 67%, bear 33%, decision buy. i kept the boring job for myself: being the pm. the whole debate is on screen in the clip.
if you want to build an AI trading system from scratch, start with this article you will end up with real market data, real backtests and a bot that trades for you 24/7
9
6
66
4,205
RetroChainer retweeted
This is f*cking gold.. A FREE MARKET-MAKING BOT TOOK 60 PAPER TRADES ON BITCOIN AND MADE $4.12. ONE SQUARE ON THE HEATMAP UNDER IT SAYS IT COULD HAVE MADE $16.85. this is hummingbot. 20.7k stars, apache-2.0, a market-making bot you run yourself. → it sits on both sides of the btc-usdt book, 0.12% above and below the price → 0.002 btc per order, paper money on binance → 29 buys, 31 sells, and the pnl is red for a while before it turns green → then it sweeps every bid and ask spread over the last 23 hours of bars honestly my favourite part is how small the number is. $4.12. nobody screenshots that. i kept the boring job for myself: picking the spread. which setting made $16.85 is on screen in the clip.
if you want to build an AI trading system from scratch, start with this article you will end up with real market data, real backtests and a bot that trades for you 24/7
9
7
99
6,255
This is f*cking gold.. A FREE MARKET-MAKING BOT TOOK 60 PAPER TRADES ON BITCOIN AND MADE $4.12. ONE SQUARE ON THE HEATMAP UNDER IT SAYS IT COULD HAVE MADE $16.85. this is hummingbot. 20.7k stars, apache-2.0, a market-making bot you run yourself. → it sits on both sides of the btc-usdt book, 0.12% above and below the price → 0.002 btc per order, paper money on binance → 29 buys, 31 sells, and the pnl is red for a while before it turns green → then it sweeps every bid and ask spread over the last 23 hours of bars honestly my favourite part is how small the number is. $4.12. nobody screenshots that. i kept the boring job for myself: picking the spread. which setting made $16.85 is on screen in the clip.
if you want to build an AI trading system from scratch, start with this article you will end up with real market data, real backtests and a bot that trades for you 24/7
9
7
99
6,255
RetroChainer retweeted
YOUR $30 GROK BOT CAN SHOP WITH A FRESH SINGLE-USE CARD EVERY TIME, READ YOUR BANK THROUGH PLAID AND FILL PASSWORDS FROM 1PASSWORD. IT STILL CAN'T SPEND A DOLLAR WITHOUT YOU. this is the grok bot a-to-z map. every feature, limit and hack on one page. → one cloud computer shared by every bot, and /workspace is the only safe folder → 21 apps to connect, from gmail to coinbase → @bot under any post sends it straight to your main bot → every spend waits for your approval honestly my favourite line is in group chats: "no owner · 20 messages, nothing done." i kept the boring job for myself: approving the spend. what "stop now" doesn't do is on screen in the clip.
13
8
87
3,816
YOUR $30 GROK BOT CAN SHOP WITH A FRESH SINGLE-USE CARD EVERY TIME, READ YOUR BANK THROUGH PLAID AND FILL PASSWORDS FROM 1PASSWORD. IT STILL CAN'T SPEND A DOLLAR WITHOUT YOU. this is the grok bot a-to-z map. every feature, limit and hack on one page. → one cloud computer shared by every bot, and /workspace is the only safe folder → 21 apps to connect, from gmail to coinbase → @bot under any post sends it straight to your main bot → every spend waits for your approval honestly my favourite line is in group chats: "no owner · 20 messages, nothing done." i kept the boring job for myself: approving the spend. what "stop now" doesn't do is on screen in the clip.
13
8
87
3,816
RetroChainer retweeted
This is f*cking gold.. A RULE WON 11 OF 15 TRADES AND TURNED $10,000 INTO $10,770. ONE BUY DID SOMETHING ELSE. it's vn. py, 46k stars, the open-source quant platform out of china. five years on amd, and the rule does one thing: buy the dip, sell the bounce. it was right 11 times. it paid 2.90% in fees to be right. and its drawdown still hit -57%. honestly a 73% win rate looks great in a screenshot. the final balance doesn't care. that one buy is on screen in the clip.
Finally... AI trading system that I trust with my money Built on Jane Street’s rules, the firm behind ~10% of US stocks 6 GrokBot + Opus 5.5 agents find, test and kill trades 24/7 while you sleep In this article, I show you how to build it:
9
14
139
8,093
This is f*cking gold.. A RULE WON 11 OF 15 TRADES AND TURNED $10,000 INTO $10,770. ONE BUY DID SOMETHING ELSE. it's vn. py, 46k stars, the open-source quant platform out of china. five years on amd, and the rule does one thing: buy the dip, sell the bounce. it was right 11 times. it paid 2.90% in fees to be right. and its drawdown still hit -57%. honestly a 73% win rate looks great in a screenshot. the final balance doesn't care. that one buy is on screen in the clip.
Finally... AI trading system that I trust with my money Built on Jane Street’s rules, the firm behind ~10% of US stocks 6 GrokBot + Opus 5.5 agents find, test and kill trades 24/7 while you sleep In this article, I show you how to build it:
9
14
139
8,093
RetroChainer retweeted
THESE 2 FREE REPOS SHOULD HONESTLY BE ILLEGAL. ONE SENTENCE TO CLAUDE CODE, 60 SECONDS OF WATCHING, AND A DESKTOP TRADING CHART IS RUNNING ON 4 EXCHANGES IN YOUR TERMINAL FOR $0. they're called rea and ccxt. both open source. here's how it works: > rea reads 18,402 trades and finds how the app builds its footprint chart > it rebuilds it in 256 lines, 12 of 12 tests passed > ccxt feeds it binance, okx, bybit and coinbase at once here's how to run it: 1 → pip install ccxt 2 → plug rea into claude code 3 → ask it to rebuild one chart in your terminal honestly the spread line is the part i keep watching: buy coinbase, sell bybit, 11.3 bps. how the replay ends is on screen in the clip. i won't say anything more. bookmark this ↓
if you want to build an AI trading system from scratch, start with this article you will end up with real market data, real backtests and a bot that trades for you 24/7
19
21
182
11,613
THESE 2 FREE REPOS SHOULD HONESTLY BE ILLEGAL. ONE SENTENCE TO CLAUDE CODE, 60 SECONDS OF WATCHING, AND A DESKTOP TRADING CHART IS RUNNING ON 4 EXCHANGES IN YOUR TERMINAL FOR $0. they're called rea and ccxt. both open source. here's how it works: > rea reads 18,402 trades and finds how the app builds its footprint chart > it rebuilds it in 256 lines, 12 of 12 tests passed > ccxt feeds it binance, okx, bybit and coinbase at once here's how to run it: 1 → pip install ccxt 2 → plug rea into claude code 3 → ask it to rebuild one chart in your terminal honestly the spread line is the part i keep watching: buy coinbase, sell bybit, 11.3 bps. how the replay ends is on screen in the clip. i won't say anything more. bookmark this ↓
if you want to build an AI trading system from scratch, start with this article you will end up with real market data, real backtests and a bot that trades for you 24/7
19
21
182
11,613
RetroChainer retweeted
LIFE OF PI NEEDED ABOUT $120 MILLION TO PUT A BOY NEXT TO A TIGER. ONE ZOO RAILING JUST PUT A WHOLE CROWD NEXT TO FOUR, AND THEY'RE ALREADY WALKING OVER. phones up, every finger pointing down. the railing bends, and they all go over. for a second the tigers just lie there in the shade. then all four get up. the bald guy in the white t-shirt just sits there. the last frame is the best one. watch how close they get.
I seriously don't understand why Hollywood still burns millions on green rooms like this one. before this, a shot like the bottom one went to a VFX team for weeks before anyone saw a cliff or a dinosaur behind the actors. that take went into Pollo Recast and came back with a jungle full of dinosaurs. made with @itsPolloAI 👇
4
4
46
1,630