Agentic Trading Desk is a local, modular trading system that combines an AI agent (via Robinhood MCP) with deterministic Python scripts to score stocks and ETFs using a three-pillar framework of trend, momentum, and macro sentiment, with the user always approving execution.
240
No data
56
0
MIT
2026-07-02
It enforces a clear separation of concerns: the AI handles data fetching and user interaction, while deterministic, zero-network-dependency Python scripts compute all technical indicators, ensuring reproducibility and speed. The three-pillar scoring system and guardrails (protected positions, mandatory confirmation) make it a practical, risk-aware tool for short-term portfolio management.
Personal trading desk for technical analysis and short-term portfolio management on stocks and ETFs. The system combines the automation and query capabilities of an Artificial Intelligence agent (via Robinhood MCP protocol) with local deterministic mathematical calculation engines in Python.
The ruling principle is: the AI fetches data and interacts with the user; the scripts perform the deterministic calculations; the user decides and approves execution.
The project is designed to operate locally and modularly. All technical indicator computations are delegated to Python 3 scripts that only use the Python standard library (stdlib), ensuring speed and zero network dependencies during execution.
graph TD
A[Robinhood MCP / API] -- Price Historicals / Quotes --> B[Claude / Agentic Core]
C[Investing.com / Web] -- 10Y-2Y Spread / News --> B
B -- JSON of Daily Closes --> D[scripts/macro_pillar.py]
B -- JSON of Closes + Holding status --> E[scripts/score.py]
D -- Injected Macro Score --> E
E -- Raw Indicators --> F[scripts/indicators.py]
E -- Three-Pillar Scorecard + Suggested Decision --> B
B -- Visualized Proposal --> G[User]
G -- Order Confirmation --> A
Each analyzed asset is scored in three independent categories with scores from -2 to +2 (for a consolidated total range of -6 to +6):
Determined in scripts/score.py using:
Determined in scripts/score.py combining:
AI-assisted trading desk for short-term technical analysis on stocks & ETFs via Robinhood MCP. Deterministic Python engines score each asset on a three-pillar framework (Trend · Momentum · Macro-Sentiment) using EMA, RSI, MACD, TRIX & Bollinger Bands. The AI fetches data; the scripts compute; the human approves every order.
Similar projects matched by category, topics, and programming language.
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.
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.
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.