User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
Jev Trade — waxmell114514
A simulated high-frequency crypto trading loop that makes its buy and sell calls with Jev: recent BTC and ETH prices and volumes go in, a typed confidence-aware decision comes out, and a cost-aware execution simulator turns it into P&L. Not live trading.
- Stars
- 2
- Language
- Python
- Reading time
- 3 min
- Published by
- Community
- Author
- waxmell114514
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is Jev Trade — aowang-ai.
Highlights
- Code owns every number and Jev owns every judgment: features and discretization reduce the tape to words, and policy.py maps answers to position units.
- Six typed questions go out in one call to POST /v1/systemone with jev-latest; the engine treats latency as a tunable, not an assumption.
- Corrects the brief: TypeSafe reports 70-500 ms end-to-end against 3-329 s for frontier models, because Jev emits every answer in one shot.
- The CLI covers backtests with baselines, one fully unpacked decision, latency sweeps, real Kraken bars, and exchange or central-bank reads via mock providers.
- Cites TypeSafe's jaggedness note: Jev is not a calculator, so mathematical logic stays in code.
Quickstart
bash
python -m jevtrade.cli backtest --baselines
python -m jevtrade.cli decideWatch out
Copy reviewed against the repo README on 2026-10-15; the digest truncates the README at the end of its command list, so there are no published P&L results to cite and the strategy numbers should not be read as performance claims. An existing catalog entry jev-trade covers aowang-ai/jev-trade, a different project, hence the owner-prefixed id.
Questions about this entry
Short answers drawn from the linked project or page.
A simulated high-frequency crypto trading loop where recent BTC and ETH prices and volumes go in, a typed confidence-aware Jev decision comes out, and a cost-aware execution simulator turns it into P&L you can inspect and argue with.
No. The governing rule from TypeSafe's own jaggedness notes is that Jev is not a calculator and mathematical logic belongs in code. Everything numeric — returns, volatility, z-scores, imbalance, fees, fills — stays in code; Jev only answers whether the tape leans one way.
It is a simulated loop with a cost-aware execution simulator: the engine models latency, gates and fills, and turns Jev's decisions into simulated P&L. The commands read market data and exchange announcements, but nothing here places live orders.
Python 3.10+, no required dependencies and no build step: run python -m jevtrade.cli backtest --baselines to run and score the loop, or python -m jevtrade.cli decide for one decision fully unpacked.
The README pushes back on the premise that Jev is slow: TypeSafe reports 70-500 ms end-to-end against 3-329 s for frontier models. The engine treats latency as tunable, and --extra-latency-ms lets you simulate a model of any speed and see what it does to the strategy.
Recent prices and volumes for BTC and ETH come from Kraken or a synthetic feed. Separate commands read exchange announcements and central banks with mock providers, and fetch --symbol ETH pulls real bars from Kraken.
The tape is discretized into words — returns, volatility, z-scores and imbalance — and sent as six typed questions in one request to POST /v1/systemone with jev-latest; the typed answers with confidence come back and policy.py maps them to units.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: A trading loop with Jev and GPT-6 Astra
X: News sentiment in a trading terminal
X: A Jev trading bot on Telegram
X: A Jev and Grok copy-trading bot
This post couldn't be loaded here — read it on X.https://x.com/Mnilax/status/2102760642872508510More Jev resources like this
A local proof of concept where Jev picks which of two conflicting signal phases gets the green light at a real Hong Kong intersection, using near real-time keyless open-data traffic sensors. A phase-timing state machine enforces minimum and maximum green, amber and all-red around the model's answer.
Jev Demos & Experiments#community#catalog-import#logicrw
An autonomous ViZDoom agent that decouples Doom's simulation from Jev SystemOne inference: the game runs at 35 ticks/sec while Jev is queried asynchronously at about 10 Hz for macro goals, targets, movement and firing decisions.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
amoghcreator/doom-jevPython
amoghcreator/doom-jevPythonTypeSafe Jev plays NetHack 5.0 with no LLM in the loop: each turn the code lists the legal moves, Jev picks one as a choice question, and a small motor translates the answer into keystrokes, with a live dashboard and Hardfought support.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
statico/jev-nethackPython
statico/jev-nethackPythonA 12,000-neuron fly-brain subgraph of the maleCNS connectome fights Jev in mk.js: the fly simulates spikes in the browser at 10 decisions per second while Jev reads the fight as JSON and answers one typed choice among seven moves.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
lavallee/mk-jev-fly-brainJavaScript
lavallee/mk-jev-fly-brainJavaScriptTwo TypeSafe System One game loops in one Python repo: Dino-Jev drives Chrome's chrome://dino/ dinosaur and Krunker-Jev runs a local Krunker-style arena, both feeding structured state to Jev and logging decisions.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
mittal-parth/jev-experimentsPython
mittal-parth/jev-experimentsPythonResearch prototype that tests where Jev can help a driving policy choose continue, observe, replan or defer: Jev receives structured text, a separate vision model handles camera images, and a local controller owns vehicle execution.
Jev Demos & Experiments#community#catalog-import#logicrw
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.