Public-Portfolio-Challenge
Unverified ML strategy on Options by austin-starks. BotFinder score 18 out of 100.
4 AI agents. One runbook. Real $25K, live and verifiable. Currently +22.85%.
Source: github
BotFinder analysis pending.
Public-Portfolio-Challenge
Public Portfolio Challenge 4 AI agents. One open runbook. Real $25K, live and verifiable. Live portfolio card — generated from current positions. Open the full dashboard → | Account value | Total return | Return vs. SPY | Max drawdown | Days live | | ---: | ---: | ---: | ---: | ---: | | $27,031.11 | +8.12% | -5.60 pp (SPY +13.72%) | −16.48% | 203 | As of September 28, 2026. Same-window comparison begins with the first stored live observation. Portfolio data · Performance data · SPY data · refreshed weekly by GitHub Actions. Quick start: Copy the live incumbent · Connect MCP → python3 start.py → paste prompt.txt into a fresh agent chat --- Contents - What is this? - Live books - Agent bakeoff - What this repo gives you - How the runbook works - What's inside - Community leaderboard - Get started - Risk disclaimer - More links --- What is this? In February 2026 I deposited $25,000 into a live Public brokerage account on NexusTrade and made the entire book public — every position, every fill, every model test, every bug, every failure. Not paper. Not a backtest screenshot. Real money, d
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
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 & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)