swing-trading-agent

Unverified ML strategy on Indices by kevmyung. BotFinder score 18 out of 100.

Multi-agent swing trading system — automated screening, research, and execution with backtesting and live trading

Source: github

Explorer/Indices/swing-trading-agent
18
Data index
IndicesMLMedium risk⚠ UnverifiedNEW

swing-trading-agent

kevmyungGitHub
From
Free
Get this bot
Net return
—
Max drawdown
—
Sharpe
—
Profit factor
—
Win rate
—
Track record
0.5y
BotFinder Analysis

BotFinder analysis pending.

About

swing-trading-agent

Swing Trading Agent An autonomous trading agent that manages a portfolio across multiple daily cycles — screening candidates, reading news, sizing positions, placing orders, and adjusting stops — without manual intervention. It supports backtesting on historical data, paper trading against live markets via Alpaca, and fully automated live trading. The agent doesn't just pick stocks. Each cycle builds on the output of the previous one: EOD signals flow into morning order decisions, which feed into intraday position management. News research, quantitative indicators, and a structured playbook all factor into every decision, and the agent manages the full lifecycle of each position from entry through exit. How It Works The agent runs three trading cycles per day, each designed for a specific decision point in the market. Each cycle is coordinated by three components, all powered by Amazon Bedrock foundation models via Strands Agents SDK: - Quant Engine — Screens the S&P 500 universe using technical indicators (RSI, MACD, ATR, Bollinger Bands, ADX) and ranks candidates by composite momen

PythonApache-2.0Open-sourceai-agentalgorithmic-tradingbacktestingllm-agentmulti-agentpaper-tradingquantitative-financestock-market
Track record

⚠ No verified equity curve — no track-record source connected.

Risk

Drawdown profile

Data unavailable — contact the owner.

Evidence

Verification ledger

Live-audited
Broker-verified
Capital-backed
Tamper-proof
Historical evolution

How the score has moved

Recalculated at each data collection. Transparency means showing the bad weeks too.

No score history is stored yet — only the current score is shown.

Reviews

Reviews & comments

No reviews collected from the source yet.

Live monitoring

⚠ No live verification account connected — ask for proof before buying.

Alerts on changes: coming soon

Prop-firm compatibility

Prop-firm compatibility not provided.

Source
kevmyung
Since 2015 · 1 bots

Open-source maintainer on GitHub.

Trust 0Profile
Score & reliability18/100
Perf data0/35
Community0/25
Evidence8/20
Recency10/10
Verification0/10

Data-completeness & trust index (not a profitability rating)

Source facts
Stars23
Forks9
Open issues0
LanguagePython
LicenseApache-2.0
Last update2026-05-15
Created2026-04-04
Alternatives

Similar bots worth comparing

58
ESCQ NAS100 Sweep M2NEW
Publisher's own bot
—
Return
−10.64%
Max DD
-14.24%
PF
0.43
⚠ Publisher Claimed
IndicesMedium
58
ESCQ NAS100 Flip M2NEW
Publisher's own bot
—
Return
−17.94%
Max DD
-23.29%
PF
0.75
⚠ Publisher Claimed
IndicesMedium
58
ESCQ NAS100 Flip M1NEW
Publisher's own bot
—
Return
−21.67%
Max DD
-27.91%
PF
0.81
⚠ Publisher Claimed
IndicesMedium