ai-drift 0.6.0

AI agent conversation drift analyzer - identifies gaps between what AI agents did and what users wanted

Drift

Test-driven development for AI workflows - define your standards, validate your project, iterate to compliance.

What It Does

Drift validates your AI agent projects against custom rules you define. No built-in opinions - you write the rules in .drift.yaml, Drift validates against them.

Quick Example

1. Create .drift.yaml with your rules:

rule_definitions:
  claude_md_exists:
    description: "Project must have CLAUDE.md"
    scope: project_level
    phases:
      - name: check_file
        type: file_exists
        file_path: CLAUDE.md
        failure_message: "CLAUDE.md is missing"

2. Run validation:

drift

3. Fix issues, re-run until green.

That's it. Define standards → validate → fix → iterate.

Installation

uv pip install ai-drift

Common Workflow

# 1. Define your standards in .drift.yaml
# 2. Run validation
drift

# 3. Generate AI prompts to create missing files
drift draft --target-rule skill_validation > prompt.md

# 4. Fix issues manually or with AI
# 5. Re-validate until green
drift

What You Can Validate

Define rules to check:

• Required files exist (CLAUDE.md, README.md, etc.)
• Link integrity (no broken file references)
• YAML frontmatter structure
• Dependency health (no redundant transitive dependencies)
• File format compliance (regex patterns)
• Content quality (with optional LLM-based rules)

Examples: See .drift.yaml in this repo.

Documentation

• Writing Rules - Define custom validation rules
• Validators Reference - Available validation types
• Draft Command - Generate AI prompts from rules
• CLI Options - Command-line reference

Development

./test.sh          # Run tests (90%+ coverage required)
./lint.sh          # Run linters
./lint.sh --fix    # Auto-fix formatting

License

MIT