quant-agent
Unverified ML strategy on Indices by yebof. BotFinder score 18 out of 100.
LLM multi-agent quantitative trading system for US equities. 9 specialized agents (8 daily + 1 quarterly meta-reflector) with schema-enforced reasoning chains, deterministic Python
Source: github
BotFinder analysis pending.
quant-agent
quant-agent LLM multi-agent quantitative trading system for US equities. Eight specialized daily agents — covering technical analysis, macroeconomic regimes, real-time news intelligence, SEC 10-Q/10-K filings, portfolio management, risk review, position management, and post-market reflection — coordinate through schema-enforced reasoning chains: every chain-of-thought step is a Pydantic minlength=1 mandatory field, so the LLM cannot skip steps or fake the audit trail. A separate quarterly Meta Reflector reviews 90 days of accumulated outcomes (themes caught vs missed, loss patterns by attributable agent, signal activity, agent hit rates) and proposes append-only edits to six of the eight agents' prompts under a 10-invariant safety system. Decisions execute via Alpaca with multi-layer risk controls — deterministic Python filters (cash-only, daily-loss circuit breaker, sector caps, correlation cluster) gate every order, and an LLM Risk Manager audits the Portfolio Manager's plan with veto power and per-symbol modifications before it reaches the broker. ⚠️ Disclaimer: This software is p
⚠ 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)