EklavyaSehraway GitHub avatar

Robinhood-Mcp-Trader

EklavyaSehraway

An automated weekly swing trading system that scans S&P 500 and ~110 ETFs with a React dashboard, uses AI (Claude on AWS Bedrock) for news-based candidate reviews, and supports optional live trading via Robinhood MCP with a paper-first toggle.

Stars

10

7-day growth

No data

Forks

0

Open issues

0

License

No data

Last updated

2026-07-13

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It combines a fully deterministic, auditable quantitative core with an advisory AI layer that can only veto or endorse candidates—never override risk rules—and fails open if the AI or news feed is unavailable.

Who it is for

  • Retail investors interested in automated swing trading
  • Developers building or evaluating open-source trading systems
  • Algorithmic traders seeking a transparent rule-based strategy
  • Traders experimenting with AI-assisted decision support

Use cases

  • Paper trading a weekly swing strategy with AI news filter
  • Testing the combination of technical indicators and large language model reviews
  • Learning how to integrate a React dashboard with a Python trading backend
  • Evaluating a risk-managed system before connecting live brokerage APIs

Strengths

  • Fully deterministic and auditable trading logic using textbook indicators (RSI, ATR, SMA, volume ratios)
  • AI review is advisory only, cannot override sizing or stops; system operates fail-open if AI fails
  • State persists to JSON files across restarts; unattended operation during US market hours
  • Built-in safety layers: market regime filter, hard 5-day time stop, max 10 positions, 1% risk per trade

Considerations

  • Live execution via Robinhood MCP is not yet wired in code—only paper trading is functional out of the box
  • Yahoo Finance data is ~15 minutes delayed, which may be acceptable for multi‑day swings but not for intraday precision
  • Requires AWS Bedrock credentials for AI analysis, incurring ~$2–5/day cost; no AI fallback uses purely quantitative logic

README quick start

Quick Start

Description

Automated weekly swing trader: S&P 500 + ETF scanner with AI news review (Claude/Bedrock), React dashboard, and Robinhood MCP integration

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482