Directory / cybort18/alpaca-regime-options-agent

cybort18/alpaca-regime-options-agent

Institutional-grade autonomous trading agent decoupling Google Gemini reasoning from a 100% deterministic Python Hard Risk Gate. Executes regime-adaptive, defined-risk options strategies via Alpaca API & FastMCP.

Reviewed New (under 90 days old) AI agent 70/100

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 02af86e, rubric v1.1.

Reviewer summary: Hackathon style agent with a deterministic risk gate (5 percent equity allocation cap) and an Alpaca paper default with a dry-run default in the CLI. The five test files are ad hoc scripts with no test functions.

Facts

Repository	https://github.com/cybort18/alpaca-regime-options-agent
Type	AI agent
Strategies	Iron condor, Credit spreads
Brokers	Alpaca
License	MIT
Language	Python
Last commit	2026-09-04 (50 days before the scan)
Last scanned	2026-10-24
Stars	0 (shown for context, never scored)

Score breakdown

Factor	Points	How it was decided
Risk limits and kill switch	10 / 20	risk/risk_gate.py applies hard checks including a 5 percent equity cap (10). No kill switch or human approval gate. Reviewer confirmed the scanner result. Scanner evidence (5, automated, can include false matches) `agent/strategy_agent.py:67` [max loss] - For Options Spreads: estimated_entry_price is net debit/credit per share, stop_loss is max loss threshold, target_price is profit target. `agent/strategy_agent.py:43` [stop loss] "stop_loss": float, `cli.py:58` [max position] print(f"Watchlist: {symbols} \| Max Positions: {args.max_pos} \| Mode: {'LIVE PAPER' if not dry_run else 'DRY-RUN SIMULATION'}") `dashboard/app.py:214` [max notional or exposure] st.caption("• Max Allocation per Trade: <= 5.0% Total Equity") `README.md:15` [position limit] - Position sizing capped at a maximum of 5.0% of total account equity.
License	15 / 15	MIT (OSI approved) Reviewer confirmed the scanner result. Scanner evidence (1, automated, can include false matches) `LICENSE:1` License file
Last commit on default branch	12 / 15	50 days since last commit Fact from the commit date, no judgment involved. Scanner evidence (1, automated, can include false matches) `default branch HEAD` 2026-09-04 (50 days ago)
Tests	0 / 15	test_*.py files are manual scripts without test functions, and CI is absent. Reviewer confirmed the scanner result.
Paper or dry-run mode	15 / 15	README documents ALPACA_PAPER=True and the CLI is dry-run unless --live is passed. Reviewer confirmed the scanner result. Scanner evidence (4, automated, can include false matches) `README.md:113` - Alpaca Trading account (Paper or Live) `.env.example:4` [paper-mode flag] ALPACA_PAPER=True `cli.py:56` [dry-run flag] dry_run = not args.live `mcp_server/server.py:89` [sandbox flag] "note": "Running in deterministic simulation sandbox.",
README quality	8 / 10	install steps, config or env vars, explains what it does, 6748 chars Reviewer confirmed the scanner result. Scanner evidence (1, automated, can include false matches) `README.md:1` README with 6748 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>=0.44.0
Total	70 / 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/cybort18--alpaca-regime-options-agent.json from it. Badges show the grade and whether it was reviewed. Maintainers may use one without asking.