Does Jev decide how much I buy or my stop levels?

No. Jev decides direction only through yes-or-no entry and exit questions. Position sizing, stop and target levels, spend limits, and max trades come from the risk preset and deterministic gates in code.

What happens if a Jev call fails mid-session?

Any Jev failure degrades to hold, and order or session errors halt the bot with the reason in the log. Deterministic stop, target, and max-loss checks also run before Jev is even asked.

Can I run it without broker API keys?

Yes for data, without API keys: log in to the broker site in a normal tab and the extension rides that session. You still paste a TypeSafe key, and live orders need paper mode explicitly unchecked.

Is this proven profitable trading advice?

No. The digest calls it an educational project, not financial advice, and warns auto-trading can lose real money. Start in paper mode and risk only what you can afford to lose.

How do I install and set it up?

Load the extension/ folder unpacked from chrome://extensions with Developer mode on, pin Jev Trader, and open its side panel. Log in to kite.zerodha.com in a normal tab so the extension rides that session, paste your TypeSafe API key, pick an NSE stock, and set the spend limit, interval, risk level, and max loss.

Does it trade real money by default?

No. Paper trading is on by default and simulates fills at LTP; you uncheck it for live orders. The bot runs only while the side panel stays open, and closing it stops trading deliberately. The max-loss setting is a kill switch that squares off and halts the bot.

What happens outside market hours or on an NSE holiday?

It trades only 09:15 to 15:30 IST, Monday to Friday. NSE holidays are not in the calendar yet, so on a holiday the exchange rejects the order and the bot surfaces the error. Any order or session error halts the bot with the reason in the log.

CommunityJev Tools & CLIs

Jev Trader — Shashank-H

Chrome side-panel bot that consults Jev each interval for trade direction on an NSE stock via the Zerodha web session, with paper trading on by default.

See highlights

Open github.com

Stars: 2
Language: JavaScript
License: AGPL-3.0
Published by: Community
Author: Shashank-H
Last verified: Oct 2026

Shashank-H/jev-trader

User repository on GitHub

View on GitHub

An automated trader using SystemOne model - TypesafeAI Jev

Forks: 1
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

This is one of several Jev listings for the same project. The canonical entry is Jev Trader — jarrodwatts.

About this project

A Chrome extension (side panel) that auto-trades with TypeSafe AI's Jev as the decision maker. Zerodha Kite is the only broker for now — via your active browser session (no Kite Connect API keys needed). The broker layer is a factory, so adding more brokers later is a new file + one register() call. Load unpacked → select the extension/ folder. Pin Jev Trader and click the toolbar icon to open the side panel. Log in to kite.zerodha.com in a normal tab (the extension rides that session — no API keys).

Quoted from the project's README. Read the full README.

Tagscommunity github

Works forJev for Classification

Used inJev for Software & DevTools

Languages: JavaScript

Highlights

Rides the active Zerodha browser session with a broker factory for adding more brokers later.
Computes local indicators and checks hard exits and kill switches before consulting Jev.
Asks direction-only yes-or-no questions per interval, with short selling strictly opt-in.
Keeps paper trading on by default and stops when the side panel closes as a fail-safe.

Watch out

Educational project using a broker web session that can break if Zerodha changes endpoints; live orders risk real money. 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.

More Jev resources like this

using-typesafe-and-pinecone

Example collection pairing Pinecone retrieval with Jev judgments, including a reranking demo that narrows full-text candidates by natural-language criteria.