User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Tools & CLIs
Jev Trader — renatosousa
Real-time market analysis where a local Node bridge calls Jev through the Vercel AI Gateway: headline sentiment, plus buy, sell or hold bias with strength and conviction for an FX, metals, energy, rates and crypto basket fed from MetaTrader5, with a local dashboard.
- Stars
- 0
- Language
- Python
- Published by
- Community
- Author
- renatosousa
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is Jev Trader — jarrodwatts.
About this project
Análise de mercado em tempo real usando o Jev (System One model da TypeSafe) via Vercel AI Gateway. Sentimento de notícias (sentiment.py / sentiment.mjs) — classifica manchetes por relevância e intensidade de sentimento (bearish → bullish). Sinal de compra/venda (signals/) — para uma cesta de ativos (FX, metais, energia, juros, crypto) via dados do MetaTrader5, gera viés direcional (comprar/vender/manter) com força e convicção.
Quoted from the project's README. Read the full README.
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- Python
Highlights
- sentiment.py and sentiment.mjs classify headlines by relevance and sentiment intensity, bearish to bullish.
- signals/ turns MetaTrader5 data into comprar, vender or manter with strength and conviction per asset.
- The Node bridge on 127.0.0.1:8787 exists because the official MetaTrader5 package is Windows-only.
- Real calls are spaced 10s apart by default, changeable via JEV_MIN_INTERVAL_MS or POST /config.
Watch out
The output is a directional label, not a position: the README describes comprar, vender and manter with strength and conviction and nothing about order execution, sizing, risk limits or backtesting, so nothing here places a trade. Every call goes through the Vercel AI Gateway rather than TypeSafe directly, which is why the cost section is about Gateway credits - the README warns the free tier blocks after a few calls and resets later. On Linux the documented path to live data runs Python inside Wine: enable i386, create a win64 prefix, install vcrun2022, install the MT5 terminal, drop in the 64-bit embeddable Python zip (the normal installer is a 32-bit stub that hangs), bootstrap pip, then pin numpy to 1.26.4 because 2.x crashes on Wine, and start mt5linux on port 18812. Always invoke /usr/lib/wine/wine64 directly rather than the generic wine command, which picks the 32-bit loader and fails with could not load kernel32.dll, status c0000135. The default basket uses generic symbol names such as USOIL and BTCUSD that no broker shares, so you must rewrite signals/instruments.py against your own broker's catalogue. The README does not state the questions asked, the thresholds behind comprar, vender or manter, the token cost of a signal, or any accuracy figure. The planned volatility and options module (IV, put wall, call wall, gamma flip, open interest) is explicitly not implemented. Copy reviewed against the repository README on 2026-10-04, not from running it.
Questions about this entry
Short answers drawn from the linked project or page.
Eight, all documented as validated in the project. Enable i386 and install wine, create a win64 prefix with wineboot, install vcrun2022 to avoid ucrtbase.dll crashes, install the MT5 terminal and log in manually, unzip the 64-bit embeddable Python build into the prefix and enable import site, bootstrap get-pip, then pip install numpy==1.26.4 MetaTrader5 mt5linux - numpy must be pinned because 2.x also crashes on Wine. Finally run the mt5linux bridge on port 18812 inside Wine and start signal_demo.py --mt5 natively. Use /usr/lib/wine/wine64 for every Wine call.
You will hit the rate limit and then wait. The bridge spaces real Jev calls 10 seconds apart by default specifically to avoid tripping the Gateway free tier, and you can loosen or tighten that with JEV_MIN_INTERVAL_MS before starting or a POST to /config at runtime, with GET /config to read the current value. The README states plainly that the free tier blocks quickly after a few calls and resets after a while, so sustained or production use needs credit added.
Yes. node sentiment.mjs runs the headline sentiment path and .venv/bin/python signal_demo.py runs the buy/sell signal against synthetic data; the pytest suite in tests/ needs neither network nor the bridge and mocks the Jev response; and the dashboard defaults to SIGNAL_PROVIDER=mock, so it runs the same code path on fake data. Only --mt5, and therefore SIGNAL_PROVIDER=mt5, needs a logged-in MT5 terminal.
No. The default basket in signals/instruments.py uses generic nomenclature such as USOIL and BTCUSD, and the README states plainly that every MT5 broker has its own symbol names, so you adjust the list to match your broker's catalogue, discovering the correct names with mt5.symbols_get(). get_instrument(symbol) looks up a single asset. The basket spans FX, metals, energy, rates as a proxy, and crypto by default.
Node.js 18+, Python 3.11+, and a Vercel AI Gateway AI_GATEWAY_API_KEY; real market data needs an MT5 account, a demo serving fine. Local Ollama was only used during development and is not needed to run the project.
SIGNAL_PROVIDER defaults to mock and can be mt5 for real data, SIGNAL_SYMBOLS lists a subset, DASHBOARD_REFRESH_SECONDS defaults to 300, SIGNAL_TIMEFRAME_MINUTES to 60 and DASHBOARD_PORT to 5050; the bridge must be running.
A volatility and options module covering IV, put wall, call wall, gamma flip and open interest is planned but not implemented, and the project outputs directional labels rather than executing trades.
More Jev resources like this
44GitHub stars
Mac app that turns one short English or Japanese sentence into Ableton Live mixer, transport, clip, note, device, and track edits from a pop-up bar.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
okinaaudio/live-jevPython
okinaaudio/live-jevPython547GitHub stars
Live SEO audit that crawls a site from one homepage URL, checks 52 rules tied to Google Search Central, and asks Jev typed questions about every page to rank fixes.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
AgriciDaniel/jev-seoPython
AgriciDaniel/jev-seoPython27GitHub stars
Local-first trading journal and review harness that is read-only over markets, captures runs into frozen envelopes and evidence packs, and requires explicit human promotion before any rule returns.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
myc0576/SmartMoney-CubPython
myc0576/SmartMoney-CubPython39GitHub stars
Video tool where Jev scores subtitle segments and code assembles a short highlights cut plus a de-watered full cut with timestamped summaries.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
cclank/jevclipPython
cclank/jevclipPython30GitHub stars
Forkable weekday radar that asks Jev one yes-or-no question per interest over each new arXiv announcement and publishes a page plus RSS feed.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
Eliot5566/JEV-Paper-RadarPython
Eliot5566/JEV-Paper-RadarPython38GitHub stars
Async supervisory layer for Hermes Agent that locks Definitions of Done, proves mechanical criteria locally, and calls Jev only for unresolved semantic checks under a token budget.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
keeltrace/hermes-nervePython
keeltrace/hermes-nervePythonFrom the Jev guides
Original write-ups on what this entry is for.
The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.
Jev Tools & CLIs#gateway#vercel#cloudflare
Read article
Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.
Jev Tools & CLIs#open-models#local#onnx
Read article
Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.
Jev Tools & CLIs#classification#email#security
Read article
From the Jev community
Posts from builders shipping with Jev right now.