What is Kairos and what exchanges does it support?

An experimental Python trading bot for Kraken, Alpaca hosted paper, and isolated OKX U.S. demo/live spot, with Jev-assisted strategies alongside deterministic programs and a browser dashboard for prices, model assessments, orders, fills and equity.

What does Jev control in the bot?

Not the safeguards. The README says code enforces sizing and execution limits and Jev does not control those; model-assisted strategies use Jev, while Bollinger scalping, DCA, TWAP and rebalancing need no model calls.

How should I start it?

The README says start with dry-run: it uses real Kraken data with simulated fills and no exchange orders. Live spot execution is implemented but has not been verified with real orders, and the digest's excerpt does not include the quickstart commands.

Which accounts and markets work?

Kraken USD-quoted crypto spot with guarded limit orders, Alpaca hosted paper for USD crypto and long-only whole-share US stocks and ETFs (live unavailable), and OKX U.S. cash spot for explicitly authorized finite cycles and TWAP, with separate demo and live credentials.

What risk controls are configurable?

Starting capital, order and exposure caps, daily loss limits and reinvestment. Kraken uses authenticated account fees while Alpaca labels conservative planning estimates; settings, order intents, fills and portfolio accounting persist in SQLite.

Is it profitable or safe to use?

No claims exist. The README warns that neither model confidence nor simulated returns establish profitability, and full-allocation trading can lose the entire allocation. Hosted-demo and live execution remain unverified, and mocked tests are not qualification.

How is it deployed and licensed?

It is self-hosted with nginx Basic Auth over TLS protecting network access, and the browser dashboard includes D3 candlesticks with aligned volume, pan, zoom, crosshairs and buy/sell markers. The license is AGPL-3.0.

Jev directory

CommunityJev Tools & CLIs

Kairos

An experimental self-hosted trading bot for Kraken, Alpaca paper and OKX U.S. spot with Jev-assisted strategies beside deterministic programs. Code enforces sizing and execution limits; the README stresses Jev does not control those safeguards.

See highlights Open github.com

Stars: 1
Language: Python
License: AGPL-3.0
Reading time: 2 min
Published by: Community
Author: kyaulabs
Last verified: Oct 2026

kyaulabs/kairos

Organization repository on GitHub

View on GitHub

Experimental Python trading bot for Kraken and Alpaca hosted paper, with Jev-assisted strategies, deterministic risk controls, and a live dashboard.

Forks: 0
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.

Tagscommunity catalog-import logicrw trading self-hosted

Works forJev for Realtime control Jev for Scoring

Used inJev for Finance & Fintech

Languages: Python
Platforms: SQLite Browser
Capabilities: Open sourceSelf-hostedRequires API key

Highlights

Targets Kraken USD-quoted crypto spot, Alpaca hosted paper for USD crypto and long-only whole-share stocks/ETFs, and isolated OKX U.S. demo/live spot.
Dry-run simulates fills from real Kraken data without exchange orders; Jev strategies call the model while Bollinger, DCA, TWAP and rebalancing need no model.
Controls cover starting capital, exposure and order caps, daily loss limits and reinvestment; settings, intents, fills and accounting persist in SQLite.
A browser dashboard shows D3 candlesticks, model assessments, orders, fills and portfolio equity; nginx Basic Auth over TLS protects network access.
AGPL-3.0; the README warns that live spot execution is implemented but unverified with real orders, and full-allocation trading can lose the entire allocation.

Watch out

Copy reviewed against the truncated README on 2026-10-15; the quickstart and deployment sections were not included in the digest, so this entry does not document exact run commands. The risk statements — unverified live execution, no profitability claim — are the author's own.

Questions about this entry

Short answers drawn from the linked project or page.

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/2102760642872508510

From the Jev guides

Original write-ups on what this entry is for.

Jev at home: voice pipelines, Assist routing, and sentinels

Oct 16, 2026

How Home Assistant conversation agents, macOS voice pipelines, and an advisory sentinel put a fast typed decision in the loop — one call per utterance, thresholds in code, and a daily token budget.

Jev Tools & CLIs#home-assistant#voice#automation

Read article

Search visibility, audited by decisions

Oct 16, 2026

Jev-based SEO tools split the crawl from the call: deterministic crawlers count and parse, while typed judgments rank fixes, place internal links, score search results, and track AI-answer mentions — with costs and caveats attached.

Jev Tools & CLIs#seo#search-visibility#audits

Read article

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

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

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Kairos

Highlights

Questions about this entry

What is Kairos and what exchanges does it support?

What does Jev control in the bot?

How should I start it?

Which accounts and markets work?

What risk controls are configurable?

Is it profitable or safe to use?

How is it deployed and licensed?

Reactions & coverage

More Jev resources like this

From the Jev guides

From the Jev AI model community