Skip to main content

Sigma - Finance Research Agent

Project description

Sigma

   _____ _                   
  / ___/(_)___ _____ ___  ____ _ 
  \__ \/ / __ `/ __ `__ \/ __ `/ 
 ___/ / / /_/ / / / / / / /_/ /  
/____/_/\__, /_/ /_/ /_/\__,_/   
       /____/                

Finance Research Agent

Native macOS | Multi-Provider AI | Real-Time Data


Installation | Usage | Commands | Configuration


Overview

Sigma is an AI-powered Finance Research Agent that runs natively on macOS. Ask questions in natural language, get comprehensive market analysis, charts, and backtests in seconds.


Installation

Via Brew

brew tap desenyon/sigma
brew install sigma
# or if you want app (experimental)
brew install --cask sigma

Via pip

pip install sigma-terminal
sigma --setup

From source

git clone https://github.com/desenyon/sigma.git
cd sigma
pip install -e .
sigma --setup

Usage

Interactive Mode

sigma

Launch the full terminal interface with:

  • Natural language queries with autocomplete
  • Real-time market data
  • Interactive charts and analysis
  • Conversation history

CLI Mode

sigma ask "analyze AAPL technicals"
sigma quote AAPL MSFT GOOGL
sigma compare NVDA AMD INTC
sigma backtest TSLA --strategy macd_momentum
sigma chart SPY --period 1y

Commands

Command Description
sigma Launch interactive mode
sigma ask "<query>" Ask a question
sigma quote <symbols> Get stock quotes
sigma compare <symbols> Compare multiple stocks
sigma backtest <symbol> Run a backtest
sigma chart <symbol> Generate a chart
sigma --setup Run setup wizard
sigma --status Show configuration
sigma --list-models List available models

Interactive Commands

Command Description
/help Show available commands
/clear Clear chat history
/keys Configure API keys
/models Show available models
/provider <name> Switch AI provider
/backtest Show backtest strategies
/status Show configuration
/export Export conversation

Features

AI Providers

Provider Models Notes
Google Gemini gemini-2.0-flash, 1.5-pro Free tier available
OpenAI gpt-4o, gpt-4o-mini Best reasoning
Anthropic Claude claude-sonnet-4-20250514, Opus Deep analysis
Groq Llama 3.3 70B Ultra-fast
xAI Grok 2 Real-time knowledge
Ollama Llama, Mistral, Phi Local, private

Market Data

  • Real-time quotes and price data
  • Historical OHLCV with adjustments
  • Technical indicators (RSI, MACD, Bollinger, MAs)
  • Fundamental data and financials
  • Analyst recommendations
  • Insider and fund activity

Analysis

  • Performance metrics (Sharpe, Sortino, Calmar)
  • Risk analysis (VaR, drawdowns, volatility)
  • Sector and market overview
  • Multi-asset comparison
  • Regime detection
  • Seasonality patterns

Backtesting

Strategy Description
sma_crossover SMA 20/50 crossover
rsi_mean_reversion RSI oversold/overbought
macd_momentum MACD signal crossover
bollinger_bands Bollinger band bounce
dual_momentum Absolute + relative momentum
breakout Price breakout system

Visualization

  • Candlestick charts with volume
  • Technical overlays
  • Performance curves
  • Comparison charts

Configuration

Configuration is stored in ~/.sigma/.

Environment Variables

export GOOGLE_API_KEY="your-key"
export OPENAI_API_KEY="your-key"
export ANTHROPIC_API_KEY="your-key"

Config File

Create ~/.sigma/config.env:

DEFAULT_PROVIDER=google
DEFAULT_MODEL=gemini-2.0-flash
GOOGLE_API_KEY=your-key

Keyboard Shortcuts

Shortcut Action
Ctrl+L Clear screen
Ctrl+K Configure API keys
Ctrl+M Show models
Ctrl+C Exit
Tab Autocomplete
Up/Down History navigation

Examples

# Get a quick stock overview
sigma ask "give me a summary of AAPL"

# Technical analysis
sigma ask "what do the technicals say about NVDA?"

# Compare stocks
sigma ask "compare AAPL MSFT GOOGL performance this year"

# Backtest a strategy
sigma ask "backtest SMA crossover on SPY for 2 years"

# Market overview
sigma ask "how are the markets doing today?"

# Sector analysis
sigma ask "which sectors are performing best?"

License

Proprietary - See LICENSE


Sigma v3.2.0 - Finance Research Agent

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sigma_terminal-3.2.0.tar.gz (114.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

sigma_terminal-3.2.0-py3-none-any.whl (118.2 kB view details)

Uploaded Python 3

File details

Details for the file sigma_terminal-3.2.0.tar.gz.

File metadata

  • Download URL: sigma_terminal-3.2.0.tar.gz
  • Upload date:
  • Size: 114.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.0

File hashes

Hashes for sigma_terminal-3.2.0.tar.gz
Algorithm Hash digest
SHA256 530370cab950b6ab92b162221ac66488ea2176b42eef18498ef8551aaf425917
MD5 2fbf4060175c1321532a5c4151ecea07
BLAKE2b-256 1d5460621cc602955a3fd4b04bf433404c47c5adc829c8219f3c202801b17bcc

See more details on using hashes here.

File details

Details for the file sigma_terminal-3.2.0-py3-none-any.whl.

File metadata

  • Download URL: sigma_terminal-3.2.0-py3-none-any.whl
  • Upload date:
  • Size: 118.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.0

File hashes

Hashes for sigma_terminal-3.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 40473079acf15193bc0e5fdf3fe4b7eeebfe7aa7e0ce2c29fce5b4c80a218bb4
MD5 b3753b74619e26b584afdcbe4014aff3
BLAKE2b-256 a10bb3a0a10619a2d860614cd6d3d6259b265017980aab30be47663b5ce55ee6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page