AutoTrader: Multi-Agent Trading System

Powered by AgentEdge - Autonomous AI agents seeking trading edge

⚠️ IMPORTANT DISCLAIMER

THIS SOFTWARE IS FOR EDUCATIONAL AND RESEARCH PURPOSES ONLY.

NOT FINANCIAL ADVICE: This system does not provide financial, investment, or trading advice. All outputs from technical indicators, AI agents, and automated signals are for informational purposes only.
NOT INVESTMENT ADVICE: Do not rely on this software for investment decisions. Consult a licensed financial advisor before making any trading or investment decisions.
USE AT YOUR OWN RISK: Trading stocks and securities involves substantial risk of loss. You are solely responsible for any trading decisions and resulting gains or losses.
NO WARRANTIES: This software is provided "as-is" without any guarantees of accuracy, reliability, or profitability.
PAST PERFORMANCE ≠ FUTURE RESULTS: Historical backtesting results (36.6% return, 0.856 Sharpe) do not guarantee future performance.

By using this software, you acknowledge that you understand these risks and agree to use it solely for educational purposes.

Overview

AutoTrader is a production-ready trading platform featuring a multi-agent AI architecture powered by the AgentEdge framework. The system combines validated pure-math MACD+RSI strategies with human oversight for paper/live trading via Alpaca Markets.

💡 Core Philosophy: Pure mathematical indicators + human decision making > complex LLM sentiment analysis

🚀 Production Status (Updated 2025-11-11):

✅ VoterAgent - Production-ready with validated 0.856 Sharpe ratio, 36.6% return
✅ main.py Runner - Fully functional CLI for paper trading operations
✅ Alpaca Integration - Paper trading validated and operational
✅ Position Management - Real-time tracking with broker-as-truth reconciliation
✅ Trading Cycle - Cost-efficient daily routines (90% fewer API calls)
✅ Scheduler CLI - Interactive management interface with daemon detection
✅ YAML Configuration - All configs migrated to readable YAML format
✅ Human-in-Loop CLI - Trade approval interface (Issue #308 - COMPLETED)
🚧 Multi-Agent System - Scanner, Risk, Executor agents (planned)

Key Metrics:

Sharpe Ratio: 0.856 (excellent risk-adjusted returns)
Total Return: 36.6% (2024-2025 validation period)
Win Rate: 51.4%
Max Drawdown: -10.10%
Strategy: Pure MACD(13/34/8) + RSI(14/30/70) voting - NO LLM calls

Core AutoGen Agents: Multi-Agent Trading System

The platform implements a Microsoft AutoGen-based multi-agent architecture with specialized agents:

Production-Ready Agents

VoterAgent (src/autogen_agents/voter_agent.py) - ✅ PRODUCTION READY:

MACD Signal Generation: Optimized 13/34/8 Fibonacci parameters (fast/slow/signal)
RSI Momentum Analysis: 14-period RSI with 30/70 oversold/overbought levels
Consensus Voting: Strong signals when both indicators agree, weak when only one signals
Parameterizable Design: Flexible parameter adjustment for testing and optimization
Validated Performance: 0.856 Sharpe ratio, 36.6% return over 2024-2025 testing period
AutoGen Integration: Full message handling and tool integration capabilities

Agents in Development

ScannerAgent (src/autogen_agents/scanner_agent.py) - 🚧 IN DEVELOPMENT:

Market opportunity identification and screening
Multi-symbol analysis and ranking
Real-time market scanning capabilities

RiskAgent (src/autogen_agents/risk_agent.py) - 🚧 IN DEVELOPMENT:

Position sizing and risk management
Portfolio-level risk monitoring
Stop-loss and risk mitigation strategies

ExecutorAgent (src/autogen_agents/executor_agent.py) - 🚧 IN DEVELOPMENT:

Trade execution and order management
Alpaca API integration for paper/live trading
Order status monitoring and reporting

TradingOrchestrator (src/autogen_agents/trading_orchestrator.py) - 🚧 IN DEVELOPMENT:

Multi-agent coordination and workflow management
Decision aggregation and conflict resolution
System-wide monitoring and reporting

AutoGen Architecture

Agent Communication Framework:

Base Agent Class: Common AutoGen agent foundation with tool integration
Message Handling: Structured JSON communication between agents
Tool Integration: Market data fetching and analysis tools accessible to all agents
Parameter Management: Flexible configuration system for dynamic agent adjustment

Data Infrastructure:

Market Data Tools: Polygon.io integration through AutoGen tool system
Indicator Calculations: MACD and RSI functions integrated with agents
Cache Optimization: Intelligent caching for improved performance
Configuration System: Flexible parameter management without code changes

Validation Framework:

VoterAgent Testing: Comprehensive validation with 0.856 Sharpe performance
Parameter Optimization: Systematic testing across multiple configurations
Multi-market Testing: Validation across different market conditions
AutoGen Integration Testing: Agent communication and coordination validation

Production Architecture

Core Components

VoterAgent: ✅ Production-ready AutoGen agent with validated MACD+RSI voting (0.856 Sharpe)
Base Agent Framework: AutoGen agent foundation with tool integration and message handling
Trading Tools: MACD and RSI calculation functions optimized for AutoGen agents
Configuration System: Flexible parameter management enabling dynamic agent adjustment
Market Data Integration: Polygon.io API integration through AutoGen tool framework
Validation Suite: Comprehensive testing framework for agent performance validation

AutoGen Agents in Development:

ScannerAgent: Market opportunity identification and multi-symbol analysis
RiskAgent: Portfolio risk management and position sizing
ExecutorAgent: Trade execution and Alpaca API integration
TradingOrchestrator: Multi-agent coordination and workflow management

Data Infrastructure

Trading APIs:

Alpaca: Paper and live trading execution (real-time order management)
Polygon.io: Real-time and historical market data (WebSocket + REST)
Alpha Vantage: Fallback market data source

Technical Analysis Tools:

Enhanced Fibonacci Regime Module: Advanced market regime detection
Multi-Indicator Suite: MACD, RSI, EMA filters with validated parameters
Statistical Validation: Walk-forward analysis, Monte Carlo simulation

Data Management:

UnifiedCacheManager: 90%+ performance improvement through intelligent caching
Multi-Source Aggregation: Polygon.io primary, Alpha Vantage fallback
Real-time Pipeline: WebSocket data streaming for live decision making (coming soon)

Installation

# Python 3.10+ required
conda create -n RH2MAS python=3.10
conda activate RH2MAS

# Install dependencies
pip install -e .

Configuration

NEW: Configuration files now use YAML format for better readability. JSON format still supported for backward compatibility.

All API credentials in config/config.yaml (or config/config.json):

{
  "POLYGON_IO": "your_key_here",              // ✅ Required: Primary market data
  "ALPHA_VANTAGE_KEY": "your_key_here",       // ✅ Required: Fallback market data
  "ALPACA_PAPER_API_KEY": "your_key_here",    // ✅ Required: Paper trading
  "ALPACA_PAPER_SECRET": "your_key_here",     // ✅ Required: Paper trading secret
  "ALPACA_ENDPOINT": "https://paper-api.alpaca.markets/v2",  // ✅ Paper trading URL

  "OPEN_AI_KEY": "sk-...",                    // Optional: For future LLM-based agents
  "OPENAI_TOOL_MODEL": "gpt-4o-mini",         // Optional: Tool calling model
  "OPENAI_PROMPT_MODEL": "o3-mini",           // Optional: Reasoning model

  "GOOGLE_SEARCH_API_KEY": "...",             // Legacy: Deprecated sentiment system
  "NEWSAPI_KEY": "...",                       // Legacy: Deprecated sentiment system
  "FINNHUB_KEY": "..."                        // Legacy: Deprecated sentiment system
}

Note:

VoterAgent uses pure math calculations (MACD+RSI) - OpenAI keys NOT required for trading
LLM sentiment analysis was tested and deprecated as ineffective vs. technical indicators
This file is excluded from version control for security

Quick Start

Unified Interactive CLI (✅ NEW - Priority #1)

Default: Interactive Trading Assistant

# Launch unified interactive CLI (default)
python main.py

# Interactive session with all features:
> buy 10 AAPL              # Execute trades
> check my alerts          # Position alerts
> show portfolio           # Account status
> /schedule                # Enter scheduler management CLI
> /help                    # Show all commands
> /exit                    # Exit

Daemon Mode: Background Scheduler

# Run daily scheduler in background
python main.py --daemon

# Executes twice daily:
#   - Morning: 9:20 AM ET (position reconciliation + alerts)
#   - Evening: 3:50 PM ET (performance review)

Legacy Commands (Deprecated)

# Legacy one-shot commands (will be removed)
python main.py --legacy test-voter
python main.py --legacy check-positions
python main.py --legacy paper-trade SPY

Example Interactive Session:

🚀 Launching Interactive Trading Assistant...

======================================================================
   AutoGen Trading Assistant - Unified Interactive CLI
======================================================================

> buy 10 AAPL
⏳ Analyzing trade...
📊 AAPL @ $185.50
✅ BUY SUGGESTED
   Confidence: 65.0%
   Entry:  $185.50
   Stop:   $176.23 (-5.0%)
   Target: $200.34 (+8.0%)

Continue? [yes/no]: yes
✅ ORDER PLACED SUCCESSFULLY

> check my alerts
📊 Checking Position Alerts...
🔔 1 Alert(s) Generated:
   ⚠️  TQQQ: approaching_take_profit
      Current: $53.85
      distance_pct: 1.85%

> show portfolio
💼 Portfolio Status...
💰 Account:
   Equity: $102,450.00
   Buying Power: $52,000.00
📊 Positions (3):
   🟢 AAPL: 10 shares @ $185.50
      P/L: +$85.00 (+4.58%)

CLI Features & Commands

Interactive Help System (Issue #396)

The CLI includes a comprehensive help system with command discovery, examples, and error suggestions:

# Show all available commands grouped by category
> /help

# Get detailed help for specific commands
> /help morning-routine
> /help buy
> /help forward-test

# Search commands by keyword
> /help search config
> /help search timeframe

# View all command examples
> /help --examples

# Typo suggestions - intelligent error handling
> /help mnitor
💡 Did you mean one of these?
  - monitor          Monitor active positions
  - morning-routine  Run morning market scan and analysis

Command Categories

Workflow Commands:

morning-routine - Run morning market scan and analysis
approve / reject - Approve or reject pending trades
monitor - Monitor active positions for exit signals
evening-summary - Generate end-of-day performance report

Trading Commands:

buy SYMBOL QUANTITY - Place buy order
sell SYMBOL QUANTITY - Place sell order
cancel ORDER_ID - Cancel pending orders

Information Commands:

show portfolio - Portfolio summary and allocation
show positions - Open positions with P&L
show orders - Order history and status
show account - Account details and limits

Configuration Commands (Issue #358):

show config-file - View YAML configuration files
show config-file --file trading - View specific config
show watchlist - Show market scanner symbols
show indicators - List available technical indicators

Timeframe Commands (Issue #365):

show timeframe - Display current trading timeframe
set timeframe 1d - Change timeframe (1m, 5m, 15m, 30m, 1h, 2h, 4h, 1d, 1w, 1M)
⚠️ Only 1d timeframe is validated (0.856 Sharpe) - others are experimental

Forward Testing Commands (Issue #324):

forward-test start TEST_NAME - Start 30-day validation test
forward-test report TEST_NAME - Generate test performance report
forward-test status - Check progress of active tests

Scheduler Commands:

show scheduler - View daily scheduler status
enable scheduler - Enable automated morning/evening routines
disable scheduler - Disable automation

System Commands:

/help - Interactive help system
/exit - Exit CLI

Configuration System (Issue #358)

All trading parameters are externalized to YAML files in config_defaults/:

trading_config.yaml - Strategy parameters:

strategy_parameters:
  timeframe: "1d"  # Global timeframe setting

  macd:
    fast: 13
    slow: 34
    signal: 8
    timeframe: null  # Inherits from strategy_parameters.timeframe

  rsi:
    period: 14
    oversold: 30
    overbought: 70
    timeframe: null

  exits:
    balanced:
      take_profit: 0.08  # 8% profit target
      stop_loss: 0.05    # 5% stop loss

scanner_config.yaml - Watchlist configuration:

default_watchlist:
  core_etfs:
    - SPY
    - QQQ
    - IWM
    - VTI

  tech_giants:
    - AAPL
    - MSFT
    - NVDA
    - TSLA
    - META

View configs from CLI:

> show config-file
> show config-file --file trading
> show watchlist --category tech

Timeframe Support (Issue #365)

Configure trading timeframe for all technical analysis:

# Show current timeframe
> show timeframe

# Change timeframe
> set timeframe 1h    # Hourly
> set timeframe 15m   # 15-minute
> set timeframe 1d    # Daily (validated default)

Supported Timeframes:

1m, 5m, 15m, 30m - Scalping/day trading
1h, 2h, 4h - Intraday swing trading
1d - Daily swing/position trading (✅ validated: 0.856 Sharpe)
1w, 1M - Position/long-term trading

⚠️ Important: Only the 1d (daily) timeframe has been validated with production-quality results. Other timeframes are experimental.

Forward Testing Protocol (Issue #324)

30-day validation testing before live deployment:

# Start new forward test
> forward-test start production_validation_2025 --capital 10000

# Daily progress check
> forward-test status production_validation_2025

# Generate reports
> forward-test report production_validation_2025 --type daily
> forward-test report production_validation_2025 --type weekly --week 2
> forward-test report production_validation_2025 --type final

Validation Criteria:

✅ Sharpe Ratio > 0.7
✅ Win Rate > 50%
✅ Max Drawdown < 15%
✅ 30 consecutive trading days
✅ Consistent signal generation

Error Handling & Suggestions

The CLI provides intelligent error suggestions for typos:

> forwad-test start
❌ Command 'forwad-test' not found.

💡 Did you mean one of these?
  - forward-test start    Start a new 30-day forward test
  - forward-test report   Generate forward test reports
  - forward-test status   Show status of running forward tests

> moniter
💡 Did you mean one of these?
  - monitor               Monitor active positions
  - morning-routine       Run morning market scan

Validation & Backtesting

# VoterAgent validation experiments
python scripts/experiments/experiment_293_validation/test_voter_agent.py
python scripts/experiments/experiment_293_validation/experiment_293_retest.py

# Generate comprehensive analysis with advanced metrics
python scripts/analysis/generate_results_summary.py --advanced

Project Structure

AutoTrader-AgentEdge/
├── src/
│   ├── autogen_agents/        # AI agent implementations (built with AutoGen framework)
│   │   ├── voter_agent.py     # ✅ Production-ready MACD+RSI voting agent
│   │   ├── base_agent.py      # Base AutoGen agent with tool integration
│   │   ├── scanner_agent.py   # 🚧 Market scanning agent (in development)
│   │   ├── risk_agent.py      # 🚧 Risk management agent (in development)
│   │   ├── executor_agent.py  # 🚧 Trade execution agent (in development)
│   │   └── trading_orchestrator.py  # 🚧 Multi-agent coordinator
│   ├── trading_tools/         # Tools and functions for AutoGen agents
│   │   └── indicators.py      # MACD and RSI calculation functions
│   ├── data_sources/          # Market data integration
│   │   └── tools.py           # Market data fetching tools for agents
│   ├── deprecated/            # Legacy V0-V4 sentiment system (archived)
│   └── utils/                 # Common utilities and helpers
├── scripts/
│   ├── experiments/           # Organized experiment validation
│   │   ├── experiment_293_validation/  # VoterAgent testing and validation
│   │   └── configuration_system/       # Parameter management demos
│   ├── analysis/              # Results analysis and reporting
│   └── validation/            # General validation scripts
├── config/                    # API configuration (local only)
├── config_defaults/           # Default configuration management
├── tests/                     # Legacy test scripts
└── .cache/                    # Market data caching system

Documentation

Trading Setup:

Trading Guide - Paper and live trading setup
Risk Management - Position sizing and portfolio controls
API Integration - Alpaca and data provider setup

Scheduler & Automation:

Scheduler CLI Reference - Interactive scheduler management
GTC Scheduler Technical - Daily execution system details
Background Service Design - Future service architecture
Quick Start Guide - Getting started with automation

System Architecture:

Fibonacci Integration Guide - Complete integration documentation
Quick Reference - Essential commands and usage
Regime Detection Tools - Technical analysis modules

Reference:

Commands - All available scripts and commands
Troubleshooting - Common issues and solutions

Development Status

Production-Ready Foundation ✅

✅ VoterAgent Production Ready: AutoGen-based MACD+RSI voting agent with validated 0.856 Sharpe performance
✅ Validated Parameters: MACD 13/34/8 Fibonacci parameters optimized across tech stocks
✅ AutoGen Integration: Full Microsoft AutoGen framework integration with message handling and tool access
✅ Flexible Configuration: Dynamic parameter adjustment system without code modifications
✅ Performance Proven: 36.6% return over 2024-2025, superior performance in volatile markets
✅ Tool Integration: Market data fetching and analysis tools accessible to AutoGen agents
✅ Testing Framework: Comprehensive validation suite for agent performance testing

Active Production Development 🚧

Phase 2: Multi-Agent System Completion:

ScannerAgent - Market opportunity identification and multi-symbol analysis
RiskAgent - Portfolio risk management and position sizing logic
ExecutorAgent - Trade execution and Alpaca API integration
TradingOrchestrator - Multi-agent coordination and workflow management

Priority Development Issues:

Issue #327 - ✅ Make main.py functional (COMPLETED 2025-10-23)
Issue #287 - ✅ GTC Daily Execution System (COMPLETED 2025-11-11)
Issue #308 - ✅ CLI human-in-loop interface (COMPLETED 2025-11-11)
Issue #349 - ✅ Entry price display fix (COMPLETED 2025-11-11)
Issue #350 - 🚧 Background scheduler service (planned)
Issue #328 - JSON→YAML token optimization (future)
Issue #310 - Complete remaining AutoGen agents
Issue #316 - Event bus for agent communication
Issue #324 - Forward testing protocol
Issue #321 - Dynamic trailing stop logic

Project Evolution

Originally developed as a research framework (RH2MAS), this project has evolved into AutoTrader - a production-ready trading platform featuring the AgentEdge multi-agent architecture. The system leverages Microsoft AutoGen framework to coordinate specialized AI agents for trading decisions.

Key Advantages:

AgentEdge Multi-Agent Architecture: Coordinated AI agents working together for trading edge
Production-Ready Foundation: Validated 0.856 Sharpe performance with MACD+RSI voting logic
Flexible Parameter System: Dynamic configuration without code modifications
Extensible Design: Clean separation enabling easy addition of new specialized agents
Framework-Agnostic Core: Built on AutoGen but designed for potential framework migration
Open Source: Complete transparency in agent logic, parameters, and validation results

Recent Updates

December 2025 - Timeframe Analysis Fix (Issue #445)

✅ Completed:

Fixed timeframe not affecting MACD/RSI analysis - Different timeframes now produce different indicator values
Global TimeframeManager instance - CLI and strategy now share the same state
Timeframe in cache keys - Hourly vs daily data cached separately
Timeframe format conversion - Automatic conversion between user format ("1h") and Alpaca format ("1Hour")

🐛 Bug Fixed:

Previously, changing the timeframe via CLI (set timeframe 1h) did not affect the MACD/RSI calculations. All analysis always used daily data regardless of the timeframe setting. This was caused by:

CLI's TimeframeCommands creating its own TimeframeManager() instance
Strategy using a different global _timeframe_manager instance
They weren't sharing state!

✅ Solution:

Both CLI and strategy now use _get_timeframe_manager() to share the same global instance
Added timeframe parameter throughout the data fetching pipeline
Cache keys now include timeframe to prevent collisions

Impact: Timeframe feature now works correctly - changing to 1h timeframe fetches hourly bars and calculates indicators on hourly data.

See Issue: #445

November 2025 - Enhanced Scheduler CLI & YAML Configuration Migration

✅ Completed:

Dedicated Scheduler Management CLI with /schedule command
Interactive Configuration Editor - No manual file editing required
Real-time Daemon Status Detection - Clear distinction between config vs service state
YAML Configuration Migration - All configs now in readable YAML format
CLI Message Configuration System - Centralized UI text management
Entry Price Display Fix (Issue #349) - Accurate position tracking
Complete Documentation - Scheduler CLI reference and background service design

🚀 Key Features:

Scheduler CLI Commands:
- status - Show config state and daemon status with next run times
- config - View all scheduler settings
- edit - Interactive editor with input validation
- enable/disable - Toggle automated trading
- test morning/evening - Run routines immediately for testing
- history - View execution history with success/failure tracking
- next - See upcoming scheduled runs
UX Improvements:
- Fixed "enabled" confusion - now shows both "Config: ENABLED" and "Service: RUNNING" separately
- Clear instructions when daemon not running but config enabled
- Real-time daemon process detection using psutil
- Input validation prevents configuration errors
YAML Migration Benefits:
- Better readability for all configuration files
- Backward compatible with existing JSON configs
- config_defaults/ now contains: trading_config.yaml, scheduler_config.yaml, agent_prompts.yaml
- Template file config.example.yaml for easy API key setup

Quick Start - Scheduler Management:

# Enter scheduler management from main CLI
python main.py
> /schedule

# Check status (shows if daemon actually running)
Scheduler> status

🟢 Config: ENABLED
❌ Service: NOT RUNNING (no automatic execution)

💡 Config is enabled but daemon is not running.
   To start automatic execution:
   1. Exit this CLI
   2. Run: python main.py --daemon

# Edit configuration interactively
Scheduler> edit

# Test a routine immediately (don't wait for scheduled time)
Scheduler> test morning

# View execution history
Scheduler> history

Documentation:

Scheduler CLI Reference - Complete command guide
Background Service Design - Future self-terminating service architecture

See Issues:

Issue #349 - Entry price display fix
Issue #350 - Background service feature (planned)

November 11, 2025 - GTC Daily Execution System (Issue #287)

✅ Completed:

Automated "set it and forget it" daily trading system
Morning (9:20 AM ET) and evening (3:50 PM ET) routines
Comprehensive retry logic with exponential backoff
Robust error handling and crash recovery
systemd service and crontab deployment options
90% API call reduction through GTC orders

🚀 Key Features:

Daily Scheduling: Automated position reconciliation and stop adjustments
Retry Logic: Exponential backoff (60s, 120s, 240s) with 10% jitter
Error Handling: Task, execution, and system-level exception management
Monitoring: Detailed execution logs and status reports
Cost-Efficient: 6-10 API calls per day vs. 1,000+ with traditional polling

Quick Start:

# Test the scheduler
python src/trading/daily_scheduler.py --mode once --task morning_routine

# Install as service (systemd)
sudo scripts/deployment/install_scheduler.sh

# Or setup cron jobs
./scripts/deployment/setup_cron.sh

See:

Issue #287 for requirements
Quick Start Guide for setup
Full Documentation for details

October 23, 2025 - main.py Production Ready

✅ Completed:

Fixed all import errors and function signature issues in main.py
Validated Alpaca paper trading integration (14 shares SPY @ $657.60, +2.2% P&L)
Implemented dual OpenAI model configuration (4o-mini for tools, o3-mini for reasoning)
Updated documentation to clarify pure-math approach (no LLM sentiment)

🎯 Key Insights:

VoterAgent uses pure MACD+RSI calculations (no LLM calls) - faster, cheaper, validated
LLM sentiment analysis was tested extensively and deprecated as ineffective
Human-in-loop design: System assists humans, doesn't trade autonomously
Cost-efficient: 90% fewer API calls through intelligent batching and GTC orders

See: Issue #327 for complete details

License

This project is licensed under AGPL-3.0 - see the LICENSE file for details.

Name		Name	Last commit message	Last commit date
Latest commit History 325 Commits
.github/workflows		.github/workflows
.vscode		.vscode
config_defaults		config_defaults
docs		docs
examples		examples
reports		reports
scripts		scripts
src		src
state		state
tests		tests
.flake8		.flake8
.gitignore		.gitignore
.markdownlint.json		.markdownlint.json
.pre-commit-config.yaml		.pre-commit-config.yaml
LICENSE		LICENSE
README.md		README.md
WORK_ASSIGNMENTS.md		WORK_ASSIGNMENTS.md
main.py		main.py
pyproject.toml		pyproject.toml
requirements-dev.txt		requirements-dev.txt
requirements.txt		requirements.txt
requirements_frozen.txt		requirements_frozen.txt
setup.cfg		setup.cfg

License

iAmGiG/AutoTrader-AgentEdge

Folders and files

Latest commit

History

Repository files navigation

AutoTrader: Multi-Agent Trading System

⚠️ IMPORTANT DISCLAIMER

Overview

Core AutoGen Agents: Multi-Agent Trading System

Production-Ready Agents

Agents in Development

AutoGen Architecture

Production Architecture

Core Components

Data Infrastructure

Installation

Configuration

Quick Start

Unified Interactive CLI (✅ NEW - Priority #1)

CLI Features & Commands

Interactive Help System (Issue #396)

Command Categories

Configuration System (Issue #358)

Timeframe Support (Issue #365)

Forward Testing Protocol (Issue #324)

Error Handling & Suggestions

Validation & Backtesting

Project Structure

Documentation

Development Status

Production-Ready Foundation ✅

Active Production Development 🚧

Project Evolution

Recent Updates

December 2025 - Timeframe Analysis Fix (Issue #445)

November 2025 - Enhanced Scheduler CLI & YAML Configuration Migration

November 11, 2025 - GTC Daily Execution System (Issue #287)

October 23, 2025 - main.py Production Ready

License

About

Topics

Resources

License

Uh oh!

Stars

Watchers

Forks

Uh oh!

Contributors 2

Uh oh!

Languages