45ck

45ck / llm-quant

Public

LLM-powered paper trading system with Claude for macro ETF allocation and tamper-evident trade ledger

15
4
69% credibility
Found Mar 31, 2026 at 15 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

An AI-driven paper trading tool where Claude analyzes markets and acts as your personal portfolio manager to test strategies safely.

How It Works

1
🔍 Discover Smart Trading Helper

You hear about a friendly AI assistant that watches markets and suggests trades like a wise advisor.

2
📥 Download and Open

Grab the simple app and launch it on your computer to start your trading adventure.

3
🔗 Link Market Info

Connect free market updates so your helper sees stock prices and trends automatically.

4
⚙️ Pick Your Style

Choose easy settings like safe or bold to match how comfy you feel with ups and downs.

5
🤖 Let AI Make Trades

Watch your AI buddy decide buys and sells in pretend money, learning from real markets.

6
📊 Review Daily Updates

Get simple reports on wins, losses, and tips to see how your money would grow.

💰 Grow Your Portfolio

Celebrate steady gains over time, ready to switch to real money when confident.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 15 to 15 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is llm-quant?

llm-quant is a Python-based paper trading system that lets Claude, Anthropic's LLM, act as your portfolio manager for macro ETF allocation across equities, bonds, commodities, crypto, and forex. You feed it market data via yfinance and configs for strategies like trend following or risk parity, and it outputs trade decisions with reasoning, enforced by risk limits and a tamper-evident ledger in DuckDB. Developers get a CLI (`pq run`) for live simulation, backtesting scripts, and auto-generated reports—perfect for testing LLM quant ideas without real money.

Why is it gaining traction?

In the crowded space of llm powered applications github projects, this stands out with Claude-driven autonomous agents for real financial decisions, complete with governance gates like drawdown halts and overfitting checks (PBO/CPCV). The tamper-evident ledger builds trust for paper trading, while modular configs let you tweak universes and strategies fast. It's a practical llm quant github entry for building llm powered autonomous agents paper prototypes, skipping boilerplate data pipelines.

Who should use this?

Quant devs prototyping LLM quantization performance comparisons or llm quantization benchmarks in trading. Finance engineers exploring claude etf allocation without building fetchers or risk engines from scratch. Hobbyists backtesting macro signals on ETF ledgers before scaling to live brokers.

Verdict

Grab it if you're into llm quant github experiments—solid alpha for paper trading with Claude, but 15 stars and 0.699999988079071% credibility score signal early days; expect to tweak configs and add tests. Worth forking for llm quantization explained demos.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.