Skip to content

Conversational AI agent for repository analysis using Git history patterns. Reveals code quality evolution, complexity trends, and decay forecasting through natural language interactions. Next-generation temporal intelligence platform.

License

Notifications You must be signed in to change notification settings

Cre4T3Tiv3/gitvoyant

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

21 Commits
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

๐Ÿ”ฎ GitVoyant

AI Agent Platform for Temporal Code Intelligence
The missing evolution layer that AI code agents need

GitVoyant v0.2.0

CI Python: 3.11+ Version: v0.2.0 Status: Stable License: Apache 2.0

ByteStack Labs GitHub Stars Contributions welcome


๐Ÿš€ Quick Start

git clone https://github.com/Cre4T3Tiv3/gitvoyant.git
cd gitvoyant
make bootstrap

๐Ÿ“– Complete Setup Guide & Documentation โ†’


๐Ÿ›๏ธ Architecture

GitVoyant v0.2.0 is built using Domain-Driven Design (DDD) principles with Clean Architecture patterns, ensuring maintainable, extensible, and reliable code:

  • ๐ŸŽฏ Domain Layer: Rich entities (TemporalEvaluation) and value objects (ComplexityTrend, ConfidenceRank) with embedded business logic
  • ๐Ÿ—๏ธ Application Layer: Use cases orchestrating business workflows with clear separation of concerns
  • ๐Ÿ“ก Infrastructure Layer: Core temporal intelligence engine with Git integration and statistical analysis
  • ๐ŸŽจ Presentation Layer: CLI interface and AI agent integration with natural language capabilities

Architecture Philosophy: Clean boundaries between domain logic, infrastructure, and presentation layers enable independent evolution and testing of each component.


๐Ÿงช QA

Test Coverage: 55+%

Current Test Coverage: 55+%

  • โœ… Unit Tests: Domain entities, value objects, and core algorithms
  • โœ… Integration Tests: Full workflow testing with real Git repositories
  • โœ… Agent Tests: AI agent interaction and tool integration
  • โœ… CLI Tests: Command-line interface and intuitive output formatting

Comprehensive test suite ensures reliability across temporal analysis, Git integration, and AI agent workflows.


๐Ÿค– AI Agent Intelligence in Action

Live Temporal Intelligence: The Claude-powered agent provides conversational access to GitVoyant's temporal analysis engine:

๐Ÿ’ฌ You: "Which files in this repo need the most attention?"
๐Ÿค– Claude: Analyzing repository temporal patterns...

๐Ÿ“ฆ Repository decay risks:
src/api/handlers.py: 0.85 (HIGH RISK - complexity growing +2.3/month)
utils/data_processing.py: 0.72 (MEDIUM RISK - declining pattern detected)  
core/business_logic.py: 0.68 (MEDIUM RISK - confidence: 0.4 - limited history)

Note: Currently supports Claude AI only. Multi-LLM support (GPT-4, Gemini, Local LLMs) planned for v0.3.0.


๐Ÿš€ What's New in v0.2.0

โœ… Enhanced Temporal Intelligence Engine

  • ๐Ÿ”ฌ Confidence Scoring: Statistical confidence based on commit history depth
  • โš ๏ธ Low Confidence Warnings: Transparent reliability indicators for limited data
  • ๐Ÿ“Š Progressive Disclosure: Higher confidence with more temporal data points
  • ๐ŸŽฏ Improved Risk Assessment: Enhanced quality decay forecasting algorithms

โœ… Stable & Reliable Platform

  • ๐Ÿ—๏ธ Domain-Driven Architecture: Clean separation with rich domain entities
  • ๐Ÿ”ฎ Claude + LangChain integration for natural language interaction
  • ๐Ÿง  AI Agent Runtime: Conversational temporal intelligence analysis
  • ๐Ÿ“Š Comprehensive Testing: 55+% test coverage across all layers

๐Ÿ“ธ GitVoyant CLI in Action

๐ŸŽจ CLI Interface

GitVoyant provides a Rich-formatted CLI experience:

GitVoyant CLI

Visual Features:

  • ๐Ÿ“‹ Command Structure: Organized help system with clear options
  • ๐Ÿ” Auto-Completion: Shell completion support for enhanced productivity
  • ๐Ÿ“Š Typography: Clean terminal formatting with proper spacing

๐Ÿ”ฌ Temporal Analysis

Deep temporal analysis with statistical confidence and visual indicators.

Temporal Analysis

What You See:

  • ๐Ÿ”ฎ Banner: Welcome message with version and branding
  • ๐Ÿ“Š Info Grid: Repository stats with ๐Ÿ”๐Ÿ“Š๐Ÿ“‚ indicators
    • ๐Ÿ” Repository path
    • ๐Ÿ“Š Health score (-0.35 = improving complexity)
    • ๐Ÿ“‚ Number of evaluated files
  • ๐Ÿ“‹ Results Table: Color-coded temporal scores
    • ๐ŸŸข Green Circle: -0.35 indicates decreasing complexity
    • File paths in cyan
    • Clean table formatting

Status Messages:

  • ๐Ÿ’™ Info: "Initializing temporal analysis..." in cyan
  • โœ… Success: "Temporal evaluation complete" in green with checkmark

๐Ÿง  AI Agent

Conversational temporal intelligence powered by Claude AI.

AI Agent Temporal Analysis

Agent Experience:

  • ๐Ÿง  Natural Language: Ask questions in plain English about code quality
  • ๐Ÿ’ฌ Interactive Dialog: Real-time conversation with temporal analysis
  • ๐Ÿ“Š Detailed Analysis: Specific decay rates, risk scores, and recommendations

Conversation Flow:

๐Ÿ’ฌ You: What is the decay rate of src/gitvoyant/cli/analyze.py?

๐Ÿค– Claude: Based on the analysis:
- The file shows a negative trend of -0.35 per month, indicating decreasing complexity over time
- It has LOW exposure and a risk score of 0.00
- The analysis is based on 11 commits
- Overall, this file appears to be well-maintained with improving code quality and minimal decay risk

Agent Capabilities:

  • ๐Ÿ” File-Specific Analysis: Deep dive into individual file patterns
  • ๐Ÿ“ˆ Trend Interpretation: Explains what temporal patterns mean
  • ๐Ÿ’ก Actionable Insights: Provides specific recommendations
  • ๐Ÿ“Š Statistical Context: Includes commit counts and confidence levels

๐ŸŽฏ CLI Design

GitVoyant implements modern terminal UI principles:

๐ŸŽจ Visual Design

  • Indicators: ๐Ÿ”๐Ÿ“Š๐Ÿ“‚ for quick scanning
  • Color Coding: Green/yellow/red for pattern recognition
  • Typography: Clean spacing and alignment

โšก User Experience

  • Feedback: Status messages during operations
  • Completion: Shell auto-completion support
  • Responsive: Adapts to terminal width
  • Consistency: Unified experience across commands

๐Ÿ” Information Design

  • Hierarchy: Key information first
  • Scannable: Tables with clear headers
  • Contextual: Descriptive help and options
  • Transparent: Clear status for remote operations

๐Ÿ” Core Capabilities

1๏ธโƒฃ Temporal File Evaluation with Confidence

from gitvoyant import TemporalEvaluatorService
service = TemporalEvaluatorService()
evaluation = await service.analyze_file("src/main.py")

print(f"Quality Pattern: {evaluation.quality_pattern}")
print(f"Complexity Trend: {evaluation.complexity_tenor.slope:.2f}/month")
print(f"Confidence: {evaluation.confidence_score:.2f}")

if evaluation.confidence_warning:
    print(f"โš ๏ธ {evaluation.confidence_warning}")

2๏ธโƒฃ Repository-Level Assessment

repo = await service.analyze_repository(".")
print(f"Health Score: {repo.overall_health_score}/10.0")
print(f"Quality Distribution: {repo.quality_distribution}")

# Identify files with quality improvement patterns
improving = repo.improving_files
print(f"Files showing improvement: {len(improving)}")

3๏ธโƒฃ Claude + LangChain Integration

from gitvoyant.application.agent_runtime import create_gitvoyant_agent
agent = create_gitvoyant_agent()

response = agent.invoke({
    "input": "Which files in this repository need attention?"
})
print(response["output"])

4๏ธโƒฃ CLI Interface

# Analyze a specific file
gitvoyant analyze temporal ./repo src/main.py

# Launch interactive AI agent
gitvoyant analyze agent

# Get help
gitvoyant --help

๐Ÿ“– Complete CLI Reference โ†’


๐Ÿ”ฌ How Temporal Intelligence Works

GitVoyant's core algorithm implements sophisticated temporal pattern recognition:

1. Commit History Analysis

# Extract complexity metrics across Git history
commits = repo.iter_commits(paths=file_path, since=analysis_window)
evolution_data = [extract_metrics(commit) for commit in commits]

2. Cyclomatic Complexity Tracking

def _cyclomatic_complexity(self, ast_tree):
    complexity = 1  # Base complexity
    for node in ast.walk(ast_tree):
        if isinstance(node, (ast.If, ast.While, ast.For)):
            complexity += 1
        elif isinstance(node, ast.BoolOp):
            complexity += len(node.values) - 1
    return complexity

3. Linear Regression Trend Analysis

# Compute temporal trend using statistical analysis
complexity_trend = np.polyfit(range(len(data)), complexity_values, 1)[0]
quality_pattern = classify_pattern(complexity_trend)  # IMPROVING/DECLINING/STABLE

4. Confidence Scoring & Risk Assessment

# Enhanced confidence scoring based on data quality
if commit_count >= 10: confidence_score = 0.9
elif commit_count >= 7: confidence_score = 0.75
elif commit_count >= 5: confidence_score = 0.6
else: confidence_score = 0.4  # Low confidence warning

# Quality decay forecasting
quality_decay_forecast = min(max(complexity_growth_rate * 2, 0), 1)

Key Innovation: GitVoyant transforms raw commit data into actionable temporal intelligence through statistical analysis, pattern recognition, and predictive modeling.


๐Ÿค– The Missing Layer in AI Code Tools

Static AI: "This file has high complexity."
GitVoyant: "This file is reducing complexity monthly, this is quality engineering."

๐Ÿ“ฆ Installation & Setup

Quick Installation

git clone https://github.com/Cre4T3Tiv3/gitvoyant.git
cd gitvoyant
make bootstrap

Environment Configuration

cp .env.example .env
# Edit .env with your ANTHROPIC_API_KEY

โš ๏ธ Note: Requires ANTHROPIC_API_KEY for full AI agent features


๐Ÿ“– Documentation


๐Ÿ—บ๏ธ Roadmap

๐ŸŽฏ v0.3.0 โ€“ Multi-LLM & Enhanced Intelligence (Q3 2025)

  • ๐Ÿค– Multi-LLM Support: GPT-4, Gemini, Claude, Local LLMs (Ollama)
  • ๐Ÿ”ฌ Advanced Algorithms: R-squared confidence, trend stability metrics
  • ๐ŸŒ Multi-Language Support: JavaScript, Java, Go temporal patterns
  • ๐Ÿ“Š Enhanced Metrics: Maintainability index, technical debt scoring
  • ๐Ÿ” Pattern Mining: Cross-repository quality pattern discovery

๐Ÿš€ v0.4.0 โ€“ Enterprise Platform (Q4 2025)

  • ๐ŸŒ Web Dashboard: Interactive temporal visualization and insights
  • ๐Ÿ”” CI/CD Integration: GitHub Actions, GitLab CI temporal monitoring
  • ๐Ÿ‘ฅ Team Analytics: Developer impact analysis and collaboration patterns
  • ๐Ÿ“ˆ Predictive Models: ML-enhanced quality decay forecasting
  • ๐ŸŽฏ Custom Patterns: Organization-specific quality pattern recognition

๐ŸŒŸ v0.5.0 โ€“ AI-Native Development (Q1 2026)

  • ๐Ÿง  Agent Ecosystem: Specialized agents for different analysis domains
  • ๐Ÿ”ฎ Temporal Recommendations: AI-powered refactoring suggestions
  • ๐Ÿ“š Knowledge Base: Historical pattern learning and recommendation
  • ๐Ÿค IDE Integration: VSCode, IntelliJ temporal intelligence plugins
  • ๐ŸŒ Community Platform: Shared pattern libraries and best practices

๐Ÿ“Œ Current Limitations & Future Work

AI Integration

  • โœ… Claude AI (Anthropic) - Full support
  • ๐Ÿšง GPT-4, Gemini, Local LLMs - Planned for v0.3.0

Language Support

  • โœ… Python - Complete temporal analysis
  • ๐Ÿšง JavaScript, Java, Go - Research in progress

Confidence & Statistics

  • โœ… Commit-based confidence scoring
  • ๐Ÿšง R-squared trend stability - Enhanced algorithms planned

๐Ÿ”ฌ The Science Behind It

GitVoyant uses temporal pattern evaluation to identify code evolution signatures:

  • ๐Ÿ“ˆ Temporal Complexity Analysis โ€“ Tracks cyclomatic complexity evolution with linear regression
  • ๐ŸŽฏ Quality Pattern Recognition โ€“ Classifies IMPROVING/DECLINING/STABLE patterns with confidence scoring
  • ๐Ÿ“Š Change Pattern Analysis โ€“ Maps modification patterns to quality outcomes
  • ๐Ÿ”ฎ Risk Correlation Modeling โ€“ Predicts future maintenance burden with decay forecasting
  • ๐Ÿ‘ฅ Developer Impact Assessment โ€“ Analyzes how team changes affect code health
  • ๐Ÿ“ Statistical Confidence โ€“ Progressive disclosure based on temporal data quality

๐Ÿ“– Learn more: Temporal Analysis Explained


๐Ÿ”ฌ Research Validation

  • โœ… Temporal Pattern Recognition: IMPROVING/DECLINING/STABLE classification with statistical rigor
  • โœ… Confidence Scoring: Progressive disclosure based on temporal data quality (55+% test coverage)
  • โœ… Statistical Analysis: Linear regression trend analysis with R-squared validation
  • โœ… Real-World Ready: Handles real Git histories and large projects with graceful degradation
  • โœ… Domain-Driven Design: Rich entities and value objects encoding business logic

๐Ÿงญ Why This Research Matters

Traditional (Snapshot)

Code Review โ†’ Find Current Issues โ†’ Fix Current Issues

๐ŸŸฅ Limitation: Reactive and blind to positive evolution


GitVoyant (Temporal)

History Analysis โ†’ Pattern Recognition โ†’ Confidence Assessment โ†’ Future Guidance

โœ… Advantage: Proactive insights, quality discovery, predictive power, statistical honesty


๐Ÿงช Contributing

GitVoyant is open source and welcomes contributions! From AI agent enhancements to temporal intelligence research, there are many ways to contribute to the future of code analysis.

๐Ÿ“‹ Complete Contributing Guide โ†’ - Comprehensive guidelines, research areas, and development standards

Quick Contribution Setup

git clone https://github.com/Cre4T3Tiv3/gitvoyant.git
cd gitvoyant
make bootstrap
make dev

๐Ÿ“– Development Workflow Details โ†’

Research Areas

  • ๐Ÿ”ฌ Cross-language quality pattern mining
  • ๐Ÿค– Agent training via historical code context
  • ๐Ÿ“Š Predictive engineering effectiveness models
  • ๐Ÿ”„ CI-integrated code health monitoring
  • ๐Ÿ“ˆ Statistical confidence and trend stability
  • ๐Ÿง  Multi-LLM temporal intelligence integration

๐Ÿ“„ License

GitVoyant v0.2.0 is licensed under Apache 2.0. See LICENSE


๐Ÿ‘ค Author

๐Ÿ”ฎ GitVoyant by Jesse Moses (@Cre4T3Tiv3) at ByteStack Labs

Could temporal intelligence with statistical confidence be the missing foundation for AI-native engineering?


๐ŸŽฏ Get Started Now

git clone https://github.com/Cre4T3Tiv3/gitvoyant.git
cd gitvoyant
make bootstrap
gitvoyant analyze temporal . --help

๐Ÿ“– Complete User Guide โ†’


GitVoyant v0.2.0 - Where Temporal Intelligence Meets AI Engineering
Built with Domain-Driven Design โ€ข Powered by Statistical Analysis โ€ข Enhanced by AI

Sponsor this project

 

Packages

No packages published