Requirements Traceability for LLM-Assisted Development
Stop losing context in your AI coding sessions. ContextGit tracks requirements, detects staleness, and provides precise context extraction for Claude Code, Cursor, and similar tools. Now with MCP Server, Watch Mode, and multi-format support!
Quick install:
pip install contextgit 1,355×
Faster Search
94%
Context Reduction
<1s
Staleness Detection
13
CLI Commands
Introducing MCP Server, multi-format scanning, watch mode, and more powerful automation features
Native Model Context Protocol integration for Claude Desktop with 11 powerful tools
Track requirements in Python, JavaScript, TypeScript, and Markdown files
Real-time file system monitoring with automatic re-scanning on changes
Automatic scanning on commit and merge with configurable hooks
Analyze downstream effects when requirements change
Validate metadata without modifying the index
# Install with all features
pip install contextgit[all]
# Or install specific features
pip install contextgit[watch] # Watch mode
pip install contextgit[mcp] # MCP server
Built specifically for LLM-assisted development workflows. Keep your AI tools in sync with your requirements.
Connect business requirements to system specs, architecture decisions, code, and tests. Navigate upstream and downstream effortlessly.
Automatically detect when requirements become stale after upstream changes. Never work with outdated specs again.
Extract exactly what your LLM needs — no more, no less. Reduce token usage by up to 94% while improving accuracy.
First-class support for Claude Code and Cursor. Auto-generates .cursorrules and CLAUDE.md for seamless integration.
All commands support --format json for easy parsing by LLMs and automation scripts.
YAML-based index with deterministic output. Clean diffs, easy merges, and full version control compatibility.
Based on objective measurements from actual projects. These aren't theoretical — they're verified improvements.
| Metric | Manual | With ContextGit | Improvement |
|---|---|---|---|
| Requirement search | 12.5 min | 0.55 sec | 1,355× faster |
| Staleness detection | 30-60 min | <1 sec | 1,800-3,600× faster |
| PR review time | 3-5 min | 30-60 sec | 5-10× faster |
| Context extraction | Manual copy | Automated | 14-29 min saved/task |
Everything you need to manage requirements traceability from your terminal. 13 commands to cover all workflows.
# Initialize repository
contextgit init
# Initialize + create LLM files
contextgit init --setup-llm
# Scan for metadata (MD, Python, JS/TS)
contextgit scan docs/ --recursive
# Preview changes
contextgit scan --dry-run
# Show project health
contextgit status
# Find requirements for a file
contextgit relevant-for-file src/auth.py
# Extract requirement details
contextgit extract SR-010 --format json
# Show node info
contextgit show SR-010
# Validate metadata
contextgit validate docs/ --recursive
# Analyze downstream impact
contextgit impact SR-010 --format json
# Install git hooks
contextgit hooks install
# Watch for file changes
contextgit watch docs/
Add requirements metadata to Markdown, Python, JavaScript, and TypeScript files.
--- contextgit: id: SR-010 type: system title: User authentication system status: active upstream: [BR-001] --- # System Requirement: User Authentication
""" contextgit: id: C-001 type: code title: Auth module upstream: [SR-010] """ def authenticate(email, password): pass
/** * @contextgit * id: C-002 * type: code * title: Login handler * upstream: [SR-010] */ export function handleLogin(req, res) { // implementation }
Start managing your requirements traceability today.
pip install contextgit pip install contextgit[all] contextgit init --setup-llm contextgit scan docs/ -r If you find ContextGit useful, consider supporting its development. Your support helps maintain and improve the tool!
Buy Me A Coffee