Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

stop scrolling and clone this before it gets paywalled. someone put their entire trading loop on GitHub. the model, the order logic, the dashboard. all of it. it makes one decision every ~300 milliseconds and quotes a fresh limit order on every single block. the brain is Jev. it... can't write a word. it looks at the order book and returns buy or sell with a probability. what the loop does each block: -> reads the live order book -> asks Jev: buy or sell? -> posts a post-only limit order one tick inside the touch -> replaces the last order -> waits for a taker to hit it the useful part: it never crosses the spread. fills only happen when someone else takes the order, so the bot is built to earn the spread instead of paying it. and every block is logged: the decision, the probabilities, the latency, the quote. the setup: git clone cp .env.example .env bun install bun run start -> with no private key it dry-runs: real book, real decisions, simulated fills then in .env: MODEL=jev TYPESAFE_AI_API_KEY=your-key -> swaps the built-in momentum stand-in for Jev want the full desk instead of one loop? -> QuantDinger ships Jev as a pre-trade gate: research, Python strategies, backtest, paper and live the workflow: order book in -> Jev decides -> code prices the order -> the market fills it or doesn't start here: one clone -> dry run -> watch 1,000 blocks of decisions before a single real order the catch: fast is not the same as right. quoting inside the spread can still lose money when the price moves against you. none of this is an ATM. > let the big model do the research. > let Jev make the call. > let code place the order. clone it now. dry-run it tonight. decide tomorrow.show more

kiosa

6,521 subscribers

21,466 views • 22 days ago •via X (Twitter)

Science & Technology Finance

Anya Rossi• Live Now

Private livecam show

15 Comments

Codio22 days ago

this storm looks truly terrifying

kiosa22 days ago

And colorful lol

Morty22 days ago

damn, i will try it today

kiosa22 days ago

Ez mate

0xLanister22 days ago

pure edge

kiosa22 days ago

Appreciate

Kai Lennox22 days ago

300ms decisions sound impressive, but I'd watch those 1,000 dry-run blocks first 😂

kiosa22 days ago

Crazy right?

Frits9121 days ago

Why is my feed full of larp build a bot posts. Begone

Wishchanxuegreatwealthlonglife Ming22 days ago

Great

Shesaidmewakeup22 days ago

Posting one tick inside the touch on every block means the fills you get are mostly the ones where price is about to move against you. Does the log track PnL a few blocks after each fill, or only the fills themselves? That’s the number that tells you if it earns the spread.

kiosa22 days ago

You just need faster software

Sophia f,21 days ago

A 300ms decision loop quoting on every block is a latency race, not an edge. Once a few people clone it, the spread you're capturing gets competed away. What's the actual fill rate versus adverse selection on this?

SATIRE21 days ago

Incredible! The colors force the yield of my attention and ignite dopamine in my brain! I can’t help but imagine myself as a wizard trading stocks! The clever and articulate linguistic programming of this post serves as a bridge towards limitless action! You have earned my view!

Doobie21 days ago

@Eleleth_Sophia can we do anything with this???

Related Videos

this is absolutely f*cking insane Black Rock just leaked 5 GitHub repos that give you the trading desk a fund pays millions for: want a full research team arguing over every trade? -> TradingAgents: a multi-agent trading firm in one repo. analysts, researchers, a risk desk want the data terminal without the terminal bill? -> OpenBB: an open data platform for analysts, quants and AI agents want a bot that actually places the orders? -> freqtrade: free, open-source crypto trading bot with backtesting built in want the engine serious quants run in production? -> NautilusTrader: a Rust-native trading engine where the backtest and the live run use the same code want all of it in one place? -> QuantDinger: an AI trading OS. research, Python strategies, backtest, paper and live trading ~282k stars of trading infrastructure. $0 in licences. now the part worth trying. every one of these has the same slow spot: the moment before the order, where something has to say yes or no. that's where Jev goes. it can't write a word. it returns BUY / SELL / HOLD with a probability in 70 to 500 milliseconds. QuantDinger already ships it as the pre-trade gate. and one repo, jev-trader, asks it buy or sell every ~300 ms and quotes a limit order on every single block. the stack in one line: OpenBB brings the data, the agents do the research, Jev makes the call, the bot places the order. the catch: fast is not the same as right. none of this is an ATM. paper trade it first. Jev + these five is the setup to test this month. bookmark and share with a friend

this is absolutely f*cking insane Black Rock just leaked 5 GitHub repos that give you the trading desk a fund pays millions for: want a full research team arguing over every trade? -> TradingAgents: a multi-agent trading firm in one repo. analysts, researchers, a risk desk want the data terminal without the terminal bill? -> OpenBB: an open data platform for analysts, quants and AI agents want a bot that actually places the orders? -> freqtrade: free, open-source crypto trading bot with backtesting built in want the engine serious quants run in production? -> NautilusTrader: a Rust-native trading engine where the backtest and the live run use the same code want all of it in one place? -> QuantDinger: an AI trading OS. research, Python strategies, backtest, paper and live trading ~282k stars of trading infrastructure. $0 in licences. now the part worth trying. every one of these has the same slow spot: the moment before the order, where something has to say yes or no. that's where Jev goes. it can't write a word. it returns BUY / SELL / HOLD with a probability in 70 to 500 milliseconds. QuantDinger already ships it as the pre-trade gate. and one repo, jev-trader, asks it buy or sell every ~300 ms and quotes a limit order on every single block. the stack in one line: OpenBB brings the data, the agents do the research, Jev makes the call, the bot places the order. the catch: fast is not the same as right. none of this is an ATM. paper trade it first. Jev + these five is the setup to test this month. bookmark and share with a friend

kiosa

30,442 views • 25 days ago

this is pure f*cking AI treasure 5 GitHub repos that give you the trading algo Wall Street pays millions dollars: want the engine serious quants run in production? -> NautilusTrader: a Rust-native trading engine where the backtest and the live run use the same code want a full research team arguing over every trade? -> TradingAgents: a multi-agent trading firm in one repo. analysts, researchers, a risk desk want the data terminal without the terminal bill? -> OpenBB: an open data platform for analysts, quants and AI agents want a bot that actually places the orders? -> freqtrade: free, open-source crypto trading bot with backtesting built in want all of it in one place? -> QuantDinger: an AI trading OS. research, Python strategies, backtest, paper and live trading ~282k stars of trading infrastructure. $0 in licences. now the part worth trying. every one of these has the same slow spot: the moment before the order, where something has to say yes or no. that's where Jev goes. it can't write a word. it returns BUY / SELL / HOLD with a probability in 70 to 500 milliseconds. QuantDinger already ships it as the pre-trade gate. and one repo, jev-trader, asks it buy or sell every ~300 ms and quotes a limit order on every single block. the stack in one line: OpenBB brings the data, the agents do the research, Jev makes the call, the bot places the order. the catch: fast is not the same as right. none of this is an ATM. paper trade it first. Jev + Claude + these 5 is the setup to test this month. check each repo before you install. save this.

this is pure f*cking AI treasure 5 GitHub repos that give you the trading algo Wall Street pays millions dollars: want the engine serious quants run in production? -> NautilusTrader: a Rust-native trading engine where the backtest and the live run use the same code want a full research team arguing over every trade? -> TradingAgents: a multi-agent trading firm in one repo. analysts, researchers, a risk desk want the data terminal without the terminal bill? -> OpenBB: an open data platform for analysts, quants and AI agents want a bot that actually places the orders? -> freqtrade: free, open-source crypto trading bot with backtesting built in want all of it in one place? -> QuantDinger: an AI trading OS. research, Python strategies, backtest, paper and live trading ~282k stars of trading infrastructure. $0 in licences. now the part worth trying. every one of these has the same slow spot: the moment before the order, where something has to say yes or no. that's where Jev goes. it can't write a word. it returns BUY / SELL / HOLD with a probability in 70 to 500 milliseconds. QuantDinger already ships it as the pre-trade gate. and one repo, jev-trader, asks it buy or sell every ~300 ms and quotes a limit order on every single block. the stack in one line: OpenBB brings the data, the agents do the research, Jev makes the call, the bot places the order. the catch: fast is not the same as right. none of this is an ATM. paper trade it first. Jev + Claude + these 5 is the setup to test this month. check each repo before you install. save this.

kiosa

22,061 views • 24 days ago

Jev builds the MOST POWERFUL trading agents and someone JUST open sourced jev-trader, a fully working 24/7 trading bot with Jev along with COMPLETE low latency CODEBASE WHAT THIS MEANS FOR YOU - you no longer have to build a trading bot with Jev from scratch, you just clone this and make it yours here is how you make your own Jev trading bot with this repo: 1. clone it and run three commands, it boots straight into dry run mode with real book data, real decisions, and simulated fills so you can watch it think with zero capital 2. drop in your Jev API key and the model starts answering buy or sell on every block with calibrated probabilities in 81 milliseconds 3. swap the book reader for your own venue, the model interface is clean so any order book that returns bids and asks plugs straight in 4. tune the decision cadence and horizon, ask the model every N blocks about the move over the next M, so you control how aggressive the engine trades 5. the hot loop already fits one block with exactly two round trips, one to read the book, one to send the order, nothing else on the path, this is the institutional latency discipline most retail bots never reach 6. plug in the live server and every block, every decision, every fill streams to a public dashboard so you watch your engine run the whole point is this repo hands you HARDEST part for FREE - > the low latency engine the COMPLETE breakdown of how i turned this into hedge fund grade HFT trading system is in my article below:

Jev builds the MOST POWERFUL trading agents and someone JUST open sourced jev-trader, a fully working 24/7 trading bot with Jev along with COMPLETE low latency CODEBASE WHAT THIS MEANS FOR YOU - you no longer have to build a trading bot with Jev from scratch, you just clone this and make it yours here is how you make your own Jev trading bot with this repo: 1. clone it and run three commands, it boots straight into dry run mode with real book data, real decisions, and simulated fills so you can watch it think with zero capital 2. drop in your Jev API key and the model starts answering buy or sell on every block with calibrated probabilities in 81 milliseconds 3. swap the book reader for your own venue, the model interface is clean so any order book that returns bids and asks plugs straight in 4. tune the decision cadence and horizon, ask the model every N blocks about the move over the next M, so you control how aggressive the engine trades 5. the hot loop already fits one block with exactly two round trips, one to read the book, one to send the order, nothing else on the path, this is the institutional latency discipline most retail bots never reach 6. plug in the live server and every block, every decision, every fill streams to a public dashboard so you watch your engine run the whole point is this repo hands you HARDEST part for FREE - > the low latency engine the COMPLETE breakdown of how i turned this into hedge fund grade HFT trading system is in my article below:

Roan

174,283 views • 1 month ago

this is absolutely f*cking insane Black Rock just leaked 4 GitHub repos that give you the trading desk a fund pays millions for: want a full research team arguing over every trade? -> TradingAgents: a multi-agent trading firm in one repo. analysts, researchers, a risk desk want the data terminal without the terminal bill? -> OpenBB: an open data platform for analysts, quants and AI agents want a bot that actually places the orders? -> freqtrade: free, open-source crypto trading bot with backtesting built in want all of it in one place? -> QuantDinger: an AI trading OS. research, Python strategies, backtest, paper and live trading ~282k stars of trading infrastructure. $0 in licences. now the part worth trying. every one of these has the same slow spot: the moment before the order, where something has to say yes or no. that's where Jev goes. it can't write a word. it returns BUY / SELL / HOLD with a probability in 70 to 500 milliseconds. QuantDinger already ships it as the pre-trade gate. and one repo, jev-trader, asks it buy or sell every ~300 ms and quotes a limit order on every single block. the stack in one line: OpenBB brings the data, the agents do the research, Jev makes the call, the bot places the order. the catch: fast is not the same as right. none of this is an ATM. paper trade it first. Jev + these five is the setup to test this month. bookmark and share with a friend

this is absolutely f*cking insane Black Rock just leaked 4 GitHub repos that give you the trading desk a fund pays millions for: want a full research team arguing over every trade? -> TradingAgents: a multi-agent trading firm in one repo. analysts, researchers, a risk desk want the data terminal without the terminal bill? -> OpenBB: an open data platform for analysts, quants and AI agents want a bot that actually places the orders? -> freqtrade: free, open-source crypto trading bot with backtesting built in want all of it in one place? -> QuantDinger: an AI trading OS. research, Python strategies, backtest, paper and live trading ~282k stars of trading infrastructure. $0 in licences. now the part worth trying. every one of these has the same slow spot: the moment before the order, where something has to say yes or no. that's where Jev goes. it can't write a word. it returns BUY / SELL / HOLD with a probability in 70 to 500 milliseconds. QuantDinger already ships it as the pre-trade gate. and one repo, jev-trader, asks it buy or sell every ~300 ms and quotes a limit order on every single block. the stack in one line: OpenBB brings the data, the agents do the research, Jev makes the call, the bot places the order. the catch: fast is not the same as right. none of this is an ATM. paper trade it first. Jev + these five is the setup to test this month. bookmark and share with a friend

Beaver

44,578 views • 16 days ago

Jev dropped barely a week ago and traders are already doing some wild sh*t with it. live order books. real-time signals. trading bots. entire AI hedge funds. here's what happened: > jev-trader · every ~0.3s asks Jev “buy or sell?” on Monad and trades > jev-trade · reads Hyperliquid order book -> Jev picks -> code sends the order > beebots · 3 OKX trading “bees”; every choice is Jev (paper trading by default) > QuantDinger · full AI trading OS; optional Jev gate = “should we trade at all?” > ai-hedge-fund · multi-agent “fund” with a Jev adapter for fast yes/no calls and that’s the funny part: Jev isn’t here to think. it’s here to make the call. the market moves -> Jev picks LONG / SHORT / HOLD -> code executes. no essays. no chain of thought. no expensive model debating every tiny market move. big models figure out the strategy. Jev handles the split-second calls. code makes it real.

Jev dropped barely a week ago and traders are already doing some wild sh*t with it. live order books. real-time signals. trading bots. entire AI hedge funds. here's what happened: > jev-trader · every ~0.3s asks Jev “buy or sell?” on Monad and trades > jev-trade · reads Hyperliquid order book -> Jev picks -> code sends the order > beebots · 3 OKX trading “bees”; every choice is Jev (paper trading by default) > QuantDinger · full AI trading OS; optional Jev gate = “should we trade at all?” > ai-hedge-fund · multi-agent “fund” with a Jev adapter for fast yes/no calls and that’s the funny part: Jev isn’t here to think. it’s here to make the call. the market moves -> Jev picks LONG / SHORT / HOLD -> code executes. no essays. no chain of thought. no expensive model debating every tiny market move. big models figure out the strategy. Jev handles the split-second calls. code makes it real.

kiosa

111,388 views • 1 month ago

honestly this should be f*cking illegal your LLM takes 30 seconds to think about a trade, but candle closed 29 seconds ago. Jev answers in 70 to 500 milliseconds. it can't write a word. it returns BUY / SELL / HOLD and a probability, and that's all a scalp needs. 3 repos already built on it: -> jev-trader: one AI trade decision every single block, on a live MON-USDC market -> QuantDinger: a full open-source AI trading OS with Jev built in. research, strategy, agent trading -> AIStock: "one person can become their own super-analyst" $0.042 per million input tokens. output is free. that's thousands of decisions for the price of one LLM call. the catch: fast is not the same as right. a wrong call in 200 milliseconds is still a wrong call. paper trade it first. > let the big model do the research. > let Jev pull the trigger. > let code set the stop. bookmark this before your bot is the slow one in the room.

honestly this should be f*cking illegal your LLM takes 30 seconds to think about a trade, but candle closed 29 seconds ago. Jev answers in 70 to 500 milliseconds. it can't write a word. it returns BUY / SELL / HOLD and a probability, and that's all a scalp needs. 3 repos already built on it: -> jev-trader: one AI trade decision every single block, on a live MON-USDC market -> QuantDinger: a full open-source AI trading OS with Jev built in. research, strategy, agent trading -> AIStock: "one person can become their own super-analyst" $0.042 per million input tokens. output is free. that's thousands of decisions for the price of one LLM call. the catch: fast is not the same as right. a wrong call in 200 milliseconds is still a wrong call. paper trade it first. > let the big model do the research. > let Jev pull the trigger. > let code set the stop. bookmark this before your bot is the slow one in the room.

kiosa

99,619 views • 27 days ago

honestly this should be f*cking illegal your LLM takes 30 seconds to think about a trade, but candle closed 29 seconds ago. Jev answers in 70 to 500 milliseconds. it can't write a word. it returns BUY / SELL / HOLD and a probability, and that's all a scalp needs. 3 repos already built on it: -> jev-trader: one AI trade decision every single block, on a live MON-USDC market -> QuantDinger: a full open-source AI trading OS with Jev built in. research, strategy, agent trading -> AIStock: "one person can become their own super-analyst" $0.042 per million input tokens. output is free. that's thousands of decisions for the price of one LLM call. the catch: fast is not the same as right. a wrong call in 200 milliseconds is still a wrong call. paper trade it first. > let the big model do the research. > let Jev pull the trigger. > let code set the stop. bookmark this before your bot is the slow one in the room.

honestly this should be f*cking illegal your LLM takes 30 seconds to think about a trade, but candle closed 29 seconds ago. Jev answers in 70 to 500 milliseconds. it can't write a word. it returns BUY / SELL / HOLD and a probability, and that's all a scalp needs. 3 repos already built on it: -> jev-trader: one AI trade decision every single block, on a live MON-USDC market -> QuantDinger: a full open-source AI trading OS with Jev built in. research, strategy, agent trading -> AIStock: "one person can become their own super-analyst" $0.042 per million input tokens. output is free. that's thousands of decisions for the price of one LLM call. the catch: fast is not the same as right. a wrong call in 200 milliseconds is still a wrong call. paper trade it first. > let the big model do the research. > let Jev pull the trigger. > let code set the stop. bookmark this before your bot is the slow one in the room.

Beaver

12,446 views • 6 days ago

Do you understand what just got open sourced? 5,800+ quant trading strategies for FREE along with its CODEBASE i gave these trading strategies to opus 5.5 + jev and it built me a PROFITABLE 24/7 trading agent here is how to use the repo and build AI trading bot: 1. clone the vault and get 5,806 trading strategies (spot, perps, grid, stat arb and market making) 2. open any strategy file, the math, the parameters and the source are already inside 3. point AgenKit at that file inside Claude Code with model as opus 5.5, one command and it reads the spec as ground truth 4. it will run a full engineering team and ships a production bot with risk controls 5. Jev is the live brain, it answers buy sell or hold in 81 milliseconds, calibrated, no hallucination 6. your engine sizes the trade from that confidence and fires it before the next block 7. a hard risk layer holds every limit, nothing goes live until you approve it 8. every night Opus 5.5 reviews the fills and ships a better version, so the agent improves while you sleep one model THINKS, the other REACTS and a strategy that sat locked in a vault now trades itself 24/7 the COMPLETE codebase and the EXACT Opus 5.5 + Jev trading system which I am running is in the article below:

Do you understand what just got open sourced? 5,800+ quant trading strategies for FREE along with its CODEBASE i gave these trading strategies to opus 5.5 + jev and it built me a PROFITABLE 24/7 trading agent here is how to use the repo and build AI trading bot: 1. clone the vault and get 5,806 trading strategies (spot, perps, grid, stat arb and market making) 2. open any strategy file, the math, the parameters and the source are already inside 3. point AgenKit at that file inside Claude Code with model as opus 5.5, one command and it reads the spec as ground truth 4. it will run a full engineering team and ships a production bot with risk controls 5. Jev is the live brain, it answers buy sell or hold in 81 milliseconds, calibrated, no hallucination 6. your engine sizes the trade from that confidence and fires it before the next block 7. a hard risk layer holds every limit, nothing goes live until you approve it 8. every night Opus 5.5 reviews the fills and ships a better version, so the agent improves while you sleep one model THINKS, the other REACTS and a strategy that sat locked in a vault now trades itself 24/7 the COMPLETE codebase and the EXACT Opus 5.5 + Jev trading system which I am running is in the article below:

Roan

96,820 views • 1 month ago

Jev + GPT-6 Astra just built the most TERRIFYING AI trading setup on the internet... [this article covers 90% of what is required to build quant-level systems] /1 GPT-6 Astra reads the order book, the tape and 3 correlated futures /2 Jev turns the signal into a trade and checks the risk limit /3 computer use clicks the order screen, no broker API needed /4 the full loop runs in 6 ms, signal to fill steal this setup in the article below👇

Jev + GPT-6 Astra just built the most TERRIFYING AI trading setup on the internet... [this article covers 90% of what is required to build quant-level systems] /1 GPT-6 Astra reads the order book, the tape and 3 correlated futures /2 Jev turns the signal into a trade and checks the risk limit /3 computer use clicks the order screen, no broker API needed /4 the full loop runs in 6 ms, signal to fill steal this setup in the article below👇

Avid

68,027 views • 1 month ago

this is pure f*cking gold for anyone doing Jev engineering the skill that teaches Claude Code to build on Jev the right way, from TypeSafe themselves without it, coding agents send Jev one question at a time and guess the field names with it, the order is set before a single line gets written: docs -> behaviour -> judgments -> one request -> code decides the two-page breakdown of every rule: > the failure each of its 11 instructions is there to prevent > Choice, Noul or Score, picked at a glance > a prompt skeleton you paste straight into your agent 12.2x that's how far the bill fell in TypeSafe's cookbook when 13 questions went out in one call one short file, and your agent stops paying for decisions it should have batched

this is pure f*cking gold for anyone doing Jev engineering the skill that teaches Claude Code to build on Jev the right way, from TypeSafe themselves without it, coding agents send Jev one question at a time and guess the field names with it, the order is set before a single line gets written: docs -> behaviour -> judgments -> one request -> code decides the two-page breakdown of every rule: > the failure each of its 11 instructions is there to prevent > Choice, Noul or Score, picked at a glance > a prompt skeleton you paste straight into your agent 12.2x that's how far the bill fell in TypeSafe's cookbook when 13 questions went out in one call one short file, and your agent stops paying for decisions it should have batched

Mr. Buzzoni

28,212 views • 1 month ago

GROK BOT + JEV ran 70 trades in one month with a $200 cap on each, and a $10,000 account ended at $20,000... two models build the desk, six agents run it, and one rule sits on every order: lose $200 at most, take $400 when it's there scan → vet → size → fill → hold → go Elon's Grok Bot finds the trade and fires the order Jev fires the stop before the entry exists, so no order lands without one between them sits a desk of six agents. scan finds the setup, vet throws most of them out, size puts $200 at risk and never more fills gets the order in, risk holds every stop, and chief says go or wait nobody on that floor can widen a stop the spider in the video crawls the whole desk, from the first order down to the last line of the honest part 70 trades in the month. 40 hit the target at +$400, 30 hit the stop at -$200 40 × $400 is $16,000, 30 × $200 is $6,000, and the $10,000 left over doubles the account that's 57% of trades right at two-to-one, and everything else stands on that 57% same rule and same 70 trades at 50% right is +$7,000. at 40% it's +$2,800. at 33% the month ends at -$200 a stop caps the loss on a normal day, and a gap jumps straight over it. ten stops in a row is -$2,000, and no rule here makes that impossible six agents, 70 trades, $200 at risk on each, and 100% in the one month it was right 57% of the time ↓

GROK BOT + JEV ran 70 trades in one month with a $200 cap on each, and a $10,000 account ended at $20,000... two models build the desk, six agents run it, and one rule sits on every order: lose $200 at most, take $400 when it's there scan → vet → size → fill → hold → go Elon's Grok Bot finds the trade and fires the order Jev fires the stop before the entry exists, so no order lands without one between them sits a desk of six agents. scan finds the setup, vet throws most of them out, size puts $200 at risk and never more fills gets the order in, risk holds every stop, and chief says go or wait nobody on that floor can widen a stop the spider in the video crawls the whole desk, from the first order down to the last line of the honest part 70 trades in the month. 40 hit the target at +$400, 30 hit the stop at -$200 40 × $400 is $16,000, 30 × $200 is $6,000, and the $10,000 left over doubles the account that's 57% of trades right at two-to-one, and everything else stands on that 57% same rule and same 70 trades at 50% right is +$7,000. at 40% it's +$2,800. at 33% the month ends at -$200 a stop caps the loss on a normal day, and a gap jumps straight over it. ten stops in a row is -$2,000, and no rule here makes that impossible six agents, 70 trades, $200 at risk on each, and 100% in the one month it was right 57% of the time ↓

Sprytix

15,227 views • 29 days ago

Jev founder, Diogo Almeida, just put out a PDF on building a Jev harness for coding agents the claim: 200x faster, 400x cheaper the model stopped being the bottleneck a while ago. the harness around it is where the cost and the speed actually live five decisions sit on every loop, and only one of them writes code hand this PDF and the article below to your Claude Code or Codex instance and let it rebuild its own setup your agent gets a better harness tonight, and monday looks different than it would have 👇

Jev founder, Diogo Almeida, just put out a PDF on building a Jev harness for coding agents the claim: 200x faster, 400x cheaper the model stopped being the bottleneck a while ago. the harness around it is where the cost and the speed actually live five decisions sit on every loop, and only one of them writes code hand this PDF and the article below to your Claude Code or Codex instance and let it rebuild its own setup your agent gets a better harness tonight, and monday looks different than it would have 👇

Hanako

37,887 views • 1 month ago

.DeepBook on Sui is the order book #Sui is built on with a central limit order book that lives in the base layer, so every app on the chain trades against the same book instead of running its own TODAY IT GETS A FRONT DOOR DeepBook Spot and DeepBook Predict, IN ONE APP Predict runs range-based markets (including 1-minute expiries) priced and settled on-chain against the same liquidity as spot we’re making Sui the home of global trading

.DeepBook on Sui is the order book #Sui is built on with a central limit order book that lives in the base layer, so every app on the chain trades against the same book instead of running its own TODAY IT GETS A FRONT DOOR DeepBook Spot and DeepBook Predict, IN ONE APP Predict runs range-based markets (including 1-minute expiries) priced and settled on-chain against the same liquidity as spot we’re making Sui the home of global trading

Adeniyi.sui

42,676 views • 1 month ago

OPUS 5.5 + DOTS + JEV built an armed trading bot in 60 minutes for $6.80 three agents, 1.45M tokens, and the bot had a cap, a stop and a kill switch before its first order rules → data → backtest → armed Dario's Opus 5.5 writes the strategy and the risk rules Dots pulls and cleans four years of candles Jev backtests it, sets the caps and is the only one allowed to send an order six switches flip one after another: strategy spec, data, bot code, backtest, paper trade, caps and kill switch. only the sixth lets it trade Jev holds three limits: a $2,000 daily loss cap, a 4% max position and an armed kill switch the backtest replayed 1,840 trades over four years. 58% green, 31% a year, worst drawdown -22% then fees, spread and slippage eat 45% of that, and 31% on paper becomes 17% in life at 17% a year, $100,000 a month needs $7.06M of capital so the $100k comes from the capital, and the bot only cost $6.80 not one live dollar has traded yet. sixty minutes proved the bot runs, whether it earns is still open 60 minutes, $6.80, three agents, zero live trades ↓

OPUS 5.5 + DOTS + JEV built an armed trading bot in 60 minutes for $6.80 three agents, 1.45M tokens, and the bot had a cap, a stop and a kill switch before its first order rules → data → backtest → armed Dario's Opus 5.5 writes the strategy and the risk rules Dots pulls and cleans four years of candles Jev backtests it, sets the caps and is the only one allowed to send an order six switches flip one after another: strategy spec, data, bot code, backtest, paper trade, caps and kill switch. only the sixth lets it trade Jev holds three limits: a $2,000 daily loss cap, a 4% max position and an armed kill switch the backtest replayed 1,840 trades over four years. 58% green, 31% a year, worst drawdown -22% then fees, spread and slippage eat 45% of that, and 31% on paper becomes 17% in life at 17% a year, $100,000 a month needs $7.06M of capital so the $100k comes from the capital, and the bot only cost $6.80 not one live dollar has traded yet. sixty minutes proved the bot runs, whether it earns is still open 60 minutes, $6.80, three agents, zero live trades ↓

Sprytix

13,497 views • 1 month ago

I couldn't f*cking believe this Stanford AI research team gave Claude Code a human brain setup. JEV is the fast gut brain. It scans everything in milliseconds and makes the easy calls. Claude is the slow thinking brain. It only wakes up for the hard ones. Here are the commands that wire the two together: /plugin marketplace add rashedInt32/jev-mcp /plugin install jev@jev-mcp -> Claude gets Jev as tools: classify, score, check npm install -g @dzhng/jevgrep jg "how are payments retried?" ./my-project -> ask what the code does, get the right files back. the author measured ~30% lower cost on the same tasks npx skills add altryne/jevify --skill jevify -> teaches your agent to hand the bulk yes/no work to Jev on its own > and fast-jev-compaction swaps Claude Code's summary for Jev decisions: it drops stale tool calls and keeps everything else word for word. Faster runs, smaller bills, barely any compute wasted. Save this before your next session.

I couldn't f*cking believe this Stanford AI research team gave Claude Code a human brain setup. JEV is the fast gut brain. It scans everything in milliseconds and makes the easy calls. Claude is the slow thinking brain. It only wakes up for the hard ones. Here are the commands that wire the two together: /plugin marketplace add rashedInt32/jev-mcp /plugin install jev@jev-mcp -> Claude gets Jev as tools: classify, score, check npm install -g @dzhng/jevgrep jg "how are payments retried?" ./my-project -> ask what the code does, get the right files back. the author measured ~30% lower cost on the same tasks npx skills add altryne/jevify --skill jevify -> teaches your agent to hand the bulk yes/no work to Jev on its own > and fast-jev-compaction swaps Claude Code's summary for Jev decisions: it drops stale tool calls and keeps everything else word for word. Faster runs, smaller bills, barely any compute wasted. Save this before your next session.

kiosa

86,755 views • 23 days ago

CLAUDE + JEV ENGINEERING = THE HARNESS SKILL THAT GETS AI ENGINEERS PROMOTED IN 2026 1,000 decisions on a cold frontier model cost $605 the same 1,000 through this harness cost $0.17 the core idea: Claude proposes, Jev answers, code decides every step leaves a receipt the loop: > propose - Claude writes plans and patches, and decides nothing > filter - code drops the routes your machine can't run before Jev ever sees them > answer - Jev picks from code's menu with a probability, or abstains > re-check - code checks the pick against live state. stale goes to fallback > act - the tool runs through the normal approval path > receipt - every step logged and replayable against a new policy the numbers: > 0.2s median per call > ~$0.0002 per desktop step > 49 of 49 WebMCP tasks passed the key insight: "I don't know" is a real answer here when Jev is only 38% sure, a fallback written in advance fires instead of a guess worth stealing even if you never touch Jev: > one decision the harness can check > the exact options code prepared > a defined path for when the model isn't sure > a way to measure what actually happened the engineer who can walk into a meeting and turn a $605 line into 17 cents is the one who gets asked to design the next system the model got the words, Jev got the choices, and code kept the final say

CLAUDE + JEV ENGINEERING = THE HARNESS SKILL THAT GETS AI ENGINEERS PROMOTED IN 2026 1,000 decisions on a cold frontier model cost $605 the same 1,000 through this harness cost $0.17 the core idea: Claude proposes, Jev answers, code decides every step leaves a receipt the loop: > propose - Claude writes plans and patches, and decides nothing > filter - code drops the routes your machine can't run before Jev ever sees them > answer - Jev picks from code's menu with a probability, or abstains > re-check - code checks the pick against live state. stale goes to fallback > act - the tool runs through the normal approval path > receipt - every step logged and replayable against a new policy the numbers: > 0.2s median per call > ~$0.0002 per desktop step > 49 of 49 WebMCP tasks passed the key insight: "I don't know" is a real answer here when Jev is only 38% sure, a fallback written in advance fires instead of a guess worth stealing even if you never touch Jev: > one decision the harness can check > the exact options code prepared > a defined path for when the model isn't sure > a way to measure what actually happened the engineer who can walk into a meeting and turn a $605 line into 17 cents is the one who gets asked to design the next system the model got the words, Jev got the choices, and code kept the final say

Mr. Buzzoni

32,459 views • 1 month ago

How does Jev work? Jev takes two things: your input and an output schema. The schema gives the structure of the answer you want. I send an email. My schema asks for two fields: is spam, and a category from marketing, finance, or spam. Jev returns: - is spam: 0.90 - category: spam That is a 90% chance of spam. Jev selects the category only from the list I give it. It writes no sentences. The 0.90 is a number object, so my code can use it immediately without extra processing. Jev shows no reasoning. You get the answer and nothing more, so some people do not trust it. Use Jev for choices your code must make fast and at low cost: spam or normal, buy or no buy, reply or escalate.

How does Jev work? Jev takes two things: your input and an output schema. The schema gives the structure of the answer you want. I send an email. My schema asks for two fields: is spam, and a category from marketing, finance, or spam. Jev returns: - is spam: 0.90 - category: spam That is a 90% chance of spam. Jev selects the category only from the list I give it. It writes no sentences. The 0.90 is a number object, so my code can use it immediately without extra processing. Jev shows no reasoning. You get the answer and nothing more, so some people do not trust it. Use Jev for choices your code must make fast and at low cost: spam or normal, buy or no buy, reply or escalate.

The Startup Ideas Podcast (SIP) 🧃

12,032 views • 1 month ago

this is f*cking gold 20 GitHub repos with 500K+ combined stars that will level up your JEV workflow AGENTS > jev-ultrafast: Jev picks every click and DOM target, a small LLM only types > hermes-jev-skills: routing, memory, compaction and skill picks in one pack > typesafe-computer-use: OCR reads your Mac screen, Jev picks the next click MEMORY > fast-jev-compaction: scores every tool call keep, truncate or drop instead of summarizing > jevmem: project memory for Claude Code, Cursor and Codex, updated every turn > jev-second-brain: your Obsidian vault, Jev judges which notes duplicate, revise or contradict SAFETY > jev-guard: a gate before every tool call, Jev scores the risk, you set allow, ask or deny TOOLS > skills: the official TypeSafe skill for Claude Code and Codex > system-one-adapter-python: dry-run your questions on an ordinary LLM before you burn a Jev key > jev-mcp: claim checks, screening and ranking as MCP tools > typesafe-mcp: plug Jev into any MCP client > json-render: Vercel's generative UI, where Jev picks the components OPEN MODELS > SemIf-OpenJev: semantic ifs from frozen open models kev: Jev-like models on Qwen that run on your MacBook > laya-mlx: the Laya decision engine on Apple silicon > clm: an open System One model with Choice, Noul and Score > jevlike: train your own Jev-like model TRADING > jev-trader: one buy or sell decision per Monad block START HERE > awesome-jev: the biggest map of everything built on Jev > awesome-jev-by-typesafe: use cases, patterns and starter code bookmark it before your next build

this is f*cking gold 20 GitHub repos with 500K+ combined stars that will level up your JEV workflow AGENTS > jev-ultrafast: Jev picks every click and DOM target, a small LLM only types > hermes-jev-skills: routing, memory, compaction and skill picks in one pack > typesafe-computer-use: OCR reads your Mac screen, Jev picks the next click MEMORY > fast-jev-compaction: scores every tool call keep, truncate or drop instead of summarizing > jevmem: project memory for Claude Code, Cursor and Codex, updated every turn > jev-second-brain: your Obsidian vault, Jev judges which notes duplicate, revise or contradict SAFETY > jev-guard: a gate before every tool call, Jev scores the risk, you set allow, ask or deny TOOLS > skills: the official TypeSafe skill for Claude Code and Codex > system-one-adapter-python: dry-run your questions on an ordinary LLM before you burn a Jev key > jev-mcp: claim checks, screening and ranking as MCP tools > typesafe-mcp: plug Jev into any MCP client > json-render: Vercel's generative UI, where Jev picks the components OPEN MODELS > SemIf-OpenJev: semantic ifs from frozen open models kev: Jev-like models on Qwen that run on your MacBook > laya-mlx: the Laya decision engine on Apple silicon > clm: an open System One model with Choice, Noul and Score > jevlike: train your own Jev-like model TRADING > jev-trader: one buy or sell decision per Monad block START HERE > awesome-jev: the biggest map of everything built on Jev > awesome-jev-by-typesafe: use cases, patterns and starter code bookmark it before your next build

NO1ennn

18,445 views • 1 month ago

this is pure f*cking treasure 15 GitHub repos with 116K combined stars where a model that can't write a single word makes the calls browsers. phones. cars. Minecraft. trading. agents that die if they can't pay PLUG IN -> give any agent a decision brain 01 litellm · Jev behind one proxy > 02 vercel ai sdk · experimental_evaluate > 03 pydantic-ai · TypeSafeModel > ACT -> Jev picks every move 04 jev-ultrafast · Google Flights in 7.1s > 05 mobile-jev · real Android, 9 actions in ~21s > 06 jev-voice-browser · ~300ms per spoken word > 07 jevpilot · steers up to 4x a second > 08 minecraft-agent · dragon down in 8:43, 131 Jev decisions > SURVIVE -> every decision comes with a bill 09 automaton · "if it cannot pay, it stops existing" > 10 jev-trader · one decision every ~300ms block > THINK LESS -> pay for a thought only when it's worth it 11 wakegate · the LLM sleeps until Jev says wake > 12 fast-jev-compaction · keeps or drops, rewrites nothing > 13 jev-pruner · 76K-char log -> 4K, the error line stays > 14 unclutter · hides the ads, reuses rules per site > DOUBT -> check if its "I'm sure" is true 15 Jev-Calibration · calibration error 0.117 -> 0.008 > the loop: state comes in -> Jev picks -> the big model only when it's worth it -> confidence check -> code executes -> the bill gets paid none of them need Jev to write a single word save this, then read why the smartest brain goes broke first

this is pure f*cking treasure 15 GitHub repos with 116K combined stars where a model that can't write a single word makes the calls browsers. phones. cars. Minecraft. trading. agents that die if they can't pay PLUG IN -> give any agent a decision brain 01 litellm · Jev behind one proxy > 02 vercel ai sdk · experimental_evaluate > 03 pydantic-ai · TypeSafeModel > ACT -> Jev picks every move 04 jev-ultrafast · Google Flights in 7.1s > 05 mobile-jev · real Android, 9 actions in ~21s > 06 jev-voice-browser · ~300ms per spoken word > 07 jevpilot · steers up to 4x a second > 08 minecraft-agent · dragon down in 8:43, 131 Jev decisions > SURVIVE -> every decision comes with a bill 09 automaton · "if it cannot pay, it stops existing" > 10 jev-trader · one decision every ~300ms block > THINK LESS -> pay for a thought only when it's worth it 11 wakegate · the LLM sleeps until Jev says wake > 12 fast-jev-compaction · keeps or drops, rewrites nothing > 13 jev-pruner · 76K-char log -> 4K, the error line stays > 14 unclutter · hides the ads, reuses rules per site > DOUBT -> check if its "I'm sure" is true 15 Jev-Calibration · calibration error 0.117 -> 0.008 > the loop: state comes in -> Jev picks -> the big model only when it's worth it -> confidence check -> code executes -> the bill gets paid none of them need Jev to write a single word save this, then read why the smartest brain goes broke first

Paone

32,937 views • 1 month ago

Rome, police is not afraid: it restores order and discipline. Police in Rome is not afraid. It is not afraid of the extreme left, it is not afraid of the extreme left and Muslim alliance. And when it is needed, it restores order and discipline. Watch the video. They advance, block the march and put an end to the chaos. This is the only answer that works. Order, discipline, respect.

Rome, police is not afraid: it restores order and discipline. Police in Rome is not afraid. It is not afraid of the extreme left, it is not afraid of the extreme left and Muslim alliance. And when it is needed, it restores order and discipline. Watch the video. They advance, block the march and put an end to the chaos. This is the only answer that works. Order, discipline, respect.

RadioGenoa

171,407 views • 9 days ago