Skip to content
Agents tracked: 442 Downloads (7d): 202M down 19.3% GitHub stars: 10.4M Releases (7d): 693 Agent status: 1 with issuesSince last limit reset: Claude 28d · Codex 1d Updated Oct 21, 2026

Vibe-Trading by Data Intelligence Lab, University of Hong Kong (HKUDS)

Open-source personal trading agent from HKUDS that researches markets and builds and backtests trading strategies from plain-language requests.

AI trading and investing agents New · Added to AgentGid on Oct 20, 2026Open source · MITFree to start
Price
Free (OSS)
free and open source
Popularity
#1 in Trading
Gid Score 29 / 100 · #160 of 260 ranked AI agents
Trend
Steady
usage up 4.6% over 30 days
Development
Updated recently
latest 0.1.16, 22d ago
Community
36.1K GitHub stars
2,741 package downloads a week

Usage data: latest readings Oct 19 to Oct 21, 2026, last checked Oct 21, 06:32 UTC. Date of each number

What Vibe-Trading does

It is free and open source (MIT); you pay only for the models it calls.

Key facts

MakerData Intelligence Lab, University of Hong Kong (HKUDS)
First releasedApril 2026
LicenseMIT
Main languagePython
Open issues and PRs24

Pricing

Open source under the MIT licence; check the website for any paid hosted plans.

, checked Oct 20, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?Yes (MIT)
  • Closest alternativeAI-Trader

Get started with Vibe-Trading

PyPIpip install vibe-trading-ai

These commands use the packages tracked on this page. The vendor may recommend a different installer.

Compare Vibe-Trading with another agent

vs

Vibe-Trading alternatives

All AI trading and investing agents

# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
197
AI-TraderHKUDS (Data Intelligence Lab, HKU)
22 — — — 22.9K+18/day — Free (OSS)

Head to head: Vibe-Trading vs AI-Trader

Ratings from people who use Vibe-Trading

No ratings yet. Used Vibe-Trading? Rate it and say what it is good and bad at.

Vibe-Trading news

All AI agent news

  1. New on AgentGid AgentGid

    17 agents added to AgentGid

    Hindsight, Cherry Studio, Google Workspace CLI, Cognee, Hypit, GenOffice, Ego Lite, cc-haha, Hive, Moli, Vibe-Trading, MemOS and 5 more

What changed: recent Vibe-Trading releases

4 stable releases in the last 90 days · Full changelog

0.1.16
  • Stock profiles carry the listing's own identity (#1577,
  • Volume statistics in technicalindicators (#1571,
  • Argentina (BYMA) market data (#1543,
  • Weekly and monthly bars (#1479). getmarketdata and backtests take
  • IM channels are configured from the Web UI (#1520, #1529; #1519, #1530,
  • Email and WebSocket join the guided Web UI channel setup (#1544, after
0.1.15
  • UK equity market (#1206,
  • Zerodha Kite Connect (#1193,
  • Read-only multi-broker portfolio (#1072,
  • Quant Library, fifteen additions (thanks @santhreal) — Heston (1993)
  • Brazilian Portuguese locale (#1327,
  • Nobitex and Wallex (#1263,
Earlier releases
0.1.14
  • Options Lab (#1096, closes #1095,
  • Factor Research tab in Run Detail (#1099,
  • Positions tab in Run Detail (#1097, closes #1098,
  • Tearsheet tab in Run Detail (#1091, closes #1090,
  • Interactive backtest research dashboard (#1084,
  • Strategy Discovery (#978 Phase 1 and #1007 Phase 2, refs #969, thanks
0.1.13
  • rundcf — FCFF bridge, WACC build, mid-year discounting, net-debt bridge, WACC×g sensitivity grid. Dual terminal value: each method is cross-checked against the other's implied multiple and implied g.
  • runcomps — EV bridge, LTM + calendar-year calendarisation, multiple matrix. A peer with a non-positive denominator is excluded and reported, never averaged in as a negative multiple.
  • threestatement — linked projection with a hard balance assertion, an explicit revolver plug, and an iterated interest↔debt circularity that must converge or raise.
  • getinstitutionalholdings — SEC 13F-HR books in manager / ticker-holders / top-managers modes, with quarter-over-quarter position diffs for factor use. Cover-page totals carry valueunits + basis,…
  • etfholdings — cross-market look-through. SEC N-PORT for US; for A-shares the semi-annual/annual reports carry the full book, not the quarterly top ten: 510300 returns 342 rows covering 98.66% of…
  • predictionmarket — event-contract search / event / market / history, with prices converted to implied probability and the unit labelled, so downstream never reads 0.63 as dollars. Read-only by…
0.1.12
  • Look-ahead-bias fix across all five portfolio optimizers (#487,
  • Security hardening — all 10 findings from the 2026-07-10 external audit closed (#476): AST-hardened backtest sandbox, short-lived SSE auth tickets, hardened Compose, /correlation auth + rate…
  • 80× signal-alignment vectorization (#698,
  • Opt-in TAP mode for Alpaca (#377,
  • Two new academic factors — Frazzini-Pedersen betting-against-beta (#480,
  • Strict-JSON / finite-number hardening across the backtest + tools stack (thanks @santhreal) — risk ratios stay finite when equity crosses zero (#765) or annualizes an explosive path (#739/#740);…
0.1.11
  • apiserver modularization completed — 1,103 → 371 lines (#424 closing #331,
  • Centralized env config — one Pydantic EnvConfig schema + an AST CI gate that rejects raw os.getenv outside the config layer (#440,
  • Trading 212 read-only connector (#321,
  • Security: loopback CSRF protection (#293), SSRF-guard hardening for CGNAT/mesh ranges (#389), Pillow/langchain CVE floor bumps (#390), tightened dev defaults.
  • Turnover-aware optimizer (#466,
  • analyzeimage vision tool (#464,

Vibe-Trading popularity and usage data

Vibe-Trading was downloaded 2,741 times from PyPI in the week ending Oct 19, 2026, up 46.9% on the week before and up 4.6% over the last 30 days compared with the 30 before. The GitHub repository has 36.1K stars, 2,529 of them added in the last 30 days. The latest stable release is 0.1.16, published Sep 29, 2026; there were 1 stable releases in the past 30 days.

Downloads per dayPyPI, 7-day average 392/day
GitHub starsrunning total 36.1K

Download the raw daily series: vibe-trading.csv

Gid Score breakdown

Adoption10
Community65
Attention—
Momentum52

Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.

How fresh these numbers are

NumberLatest readingLast checked
Package downloadsOct 19, 2026Oct 21, 06:31 UTC
GitHub starsOct 21, 2026Oct 21, 06:32 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

Vibe-Trading FAQ

How much does Vibe-Trading cost?

Open source under the MIT licence; check the website for any paid hosted plans.

Is Vibe-Trading open source?

Yes. Vibe-Trading is open source, released under the MIT license.

How popular is Vibe-Trading?

Vibe-Trading was downloaded 2,741 times from PyPI in the week ending Oct 19, 2026, up 46.9% on the week before and up 4.6% over the last 30 days compared with the 30 before. The GitHub repository has 36.1K stars, 2,529 of them added in the last 30 days. The latest stable release is 0.1.16, published Sep 29, 2026; there were 1 stable releases in the past 30 days.

What is the latest version of Vibe-Trading?

The latest stable release we track is 0.1.16, published on Sep 29, 2026.

What are the alternatives to Vibe-Trading?

The closest alternatives in the same category by Gid Score are AI-Trader.

For the makers of Vibe-Trading badges, corrections

Add a live badge to your README or site:

AgentGid: #1 in Trading Gid Score: 29/100 downloads: 2,741/week ▲5%

[![AgentGid: #1 in Trading](https://agentgid.com/badges/vibe-trading-rank.svg)](https://agentgid.com/agents/vibe-trading/)
[![Gid Score: 29/100](https://agentgid.com/badges/vibe-trading-score.svg)](https://agentgid.com/agents/vibe-trading/)
[![downloads: 2,741/week ▲5%](https://agentgid.com/badges/vibe-trading-downloads.svg)](https://agentgid.com/agents/vibe-trading/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

PyPI: vibe-trading-ai. GitHub: hkuds/vibe-trading. Site rank: vibetrading.wiki on the Tranco list. See data sources for how each one is collected.

Product facts and pricing were checked against: vibetrading.wiki, github.com, pypi.org.