Directory / GeorgeStatho/agentic-trading-research

GeorgeStatho/agentic-trading-research

A LLM based options trader

Reviewed AI agent 75/100

Not financial advice. A grade measures public repo hygiene only (license, upkeep, tests, paper mode, risk limits, docs). It does not measure returns, safety or suitability. Options trading can lose more than you invest. Read the full policy.

Reviewed. Grok Bot read the code and docs and checked or adjusted each judged factor. Nothing was executed. This is not a human audit. Reviewed on 2026-10-24 against commit 4d0c267, rubric v1.1.

Reviewer summary: LLM-driven research and execution loop on Alpaca. Has a buying-power cap, stop-loss logic, a position manager with a dry-run flag, and a paper switch. No kill switch found. README has install steps but no config table and no disclaimer.

Facts

Repository	https://github.com/GeorgeStatho/agentic-trading-research
Type	AI agent
Strategies	Not tagged
Brokers	Alpaca
License	GPL-3.0
Language	Python
Last commit	2026-05-23 (154 days before the scan)
Last scanned	2026-10-24
Stars	12 (shown for context, never scored)

Score breakdown

Factor	Points	How it was decided
Risk limits and kill switch	10 / 20	Buying-power cap in trade_executor.py and stop-loss logic in the option position strategy (10). No kill switch or approval gate found in code. Reviewer confirmed the scanner result. Scanner evidence (5, automated, can include false matches) `Python Scripts/services/trade_executor.py` [buying power cap] """Current open-option exposure versus the configured buying-power cap.""" `Python Scripts/trading_support/_option_positions_strategy.py` [stop loss] f"Stop-loss triggered at {stop_loss_unrealized_pl_pct:.2f}% versus floor {stop_loss_pct:.2f}%." `api_support/dashboard.py:818` [max notional or exposure] "label": "Max risk per trade", `api_support/dashboard.py:818` [risk limit] "label": "Max risk per trade", `web_dashboard/src/dashboardKpis.tsx:220` [max drawdown] title: 'Max Drawdown',
License	15 / 15	GPL-3.0 (OSI approved) Reviewer confirmed the scanner result. Scanner evidence (1, automated, can include false matches) `LICENSE:1` License file
Last commit on default branch	8 / 15	154 days since last commit Fact from the commit date, no judgment involved. Scanner evidence (1, automated, can include false matches) `default branch HEAD` 2026-05-23 (154 days ago)
Tests	10 / 15	127 test cases found in 24 test files; CI test step not found Reviewer confirmed the scanner result. Scanner evidence (3, automated, can include false matches) `tests/test_agent_payload_contracts.py:1` 7 test cases `tests/test_agent_pipeline_ranking.py:1` 4 test cases `tests/test_agent_runner_main.py:1` 5 test cases
Paper or dry-run mode	15 / 15	ALPACA_PAPER flag and a paper endpoint switch in services/config.py; position manager takes dry_run. Reviewer confirmed the scanner result. Scanner evidence (4, automated, can include false matches) `README.md:44` +--> Alpaca paper-trade execution `.env.example:7` [paper-mode flag] ALPACA_PAPER=true `Python Scripts/services/config.py` [paper endpoint] return "[link] if self.paper else "[link] `Python Scripts/services/position_manager.py` [dry-run flag] "Managed %s option positions; sell_count=%s full_sell_count=%s partial_sell_count=%s close_submitted_count=%s dry_run=%s",
README quality	7 / 10	install steps, config or env vars, 12272 chars Reviewer confirmed the scanner result. Scanner evidence (1, automated, can include false matches) `README.md:1` README with 12272 characters
Broker detection	10 / 10	Alpaca (deps, code, readme) Reviewer confirmed the scanner result. Scanner evidence (1, automated, can include false matches) `requirements.txt:1` [Alpaca: deps+code+readme] alpaca-py
Total	75 / 100	Grades: A 85+, B 70+, C 55+, D 40+, F below.

Grades measure public repo hygiene on the scan date. They say nothing about profits, safety or security. We did not run this code. Full rubric and patterns.

Something wrong?

Report a correction Request removal (maintainers)

Corrections and removals are public GitHub issues. We reply within 7 days and every change is in the repo history. Sponsors get no special treatment: see our policy.

Badge for your README

Once the site has a public address, shields.io can read /badge/georgestatho--agentic-trading-research.json from it. Badges show the grade and whether it was reviewed. Maintainers may use one without asking.