Skip to main content

AI-assisted development context management tool for maintaining consistency and productivity

Project description

Quaestor

๐Ÿ›๏ธ Context management for AI-assisted development

PyPI Version Python 3.12+ License: MIT

Quaestor provides intelligent context management and quality enforcement for AI assistants, with flexible modes for personal and team projects. Version 0.4.2 brings updated documentation and streamlined user experience.

Why Quaestor?

AI assistants like Claude are powerful but need context. Quaestor provides:

  • ๐Ÿง  Smart Context - Automatically adjusts rules based on project complexity
  • ๐ŸŽฏ Flexible Modes - Personal mode for solo work, team mode for collaboration
  • โš™๏ธ Command Customization - Override and configure commands per project
  • ๐Ÿ“Š Progress Tracking - Maintain project memory and milestones
  • โœ… Quality Enforcement - Ambient rules that work outside commands

Quick Start

# Personal mode (default) - Everything local to your project
uvx quaestor init

# Team mode - Shared commands, committed rules
uvx quaestor init --mode team

Personal Mode (Default)

Creates a self-contained setup in your project:

project/
โ”œโ”€โ”€ .claude/           # All AI files (gitignored)
โ”‚   โ”œโ”€โ”€ CLAUDE.md     # Context-aware rules
โ”‚   โ”œโ”€โ”€ commands/     # Local command copies
โ”‚   โ”‚   โ”œโ”€โ”€ task.md
โ”‚   โ”‚   โ”œโ”€โ”€ status.md
โ”‚   โ”‚   โ”œโ”€โ”€ analyze.md
โ”‚   โ”‚   โ”œโ”€โ”€ milestone.md
โ”‚   โ”‚   โ”œโ”€โ”€ check.md
โ”‚   โ”‚   โ”œโ”€โ”€ auto-commit.md
โ”‚   โ”‚   โ”œโ”€โ”€ milestone-pr.md
โ”‚   โ”‚   โ””โ”€โ”€ project-init.md
โ”‚   โ””โ”€โ”€ settings.json # Hooks configuration
โ”œโ”€โ”€ .quaestor/        # Documentation & memory
โ”‚   โ”œโ”€โ”€ ARCHITECTURE.md
โ”‚   โ”œโ”€โ”€ MEMORY.md
โ”‚   โ”œโ”€โ”€ PATTERNS.md
โ”‚   โ”œโ”€โ”€ VALIDATION.md
โ”‚   โ””โ”€โ”€ AUTOMATION.md
โ””โ”€โ”€ .gitignore        # Auto-updated

Team Mode

For shared projects with consistent standards:

project/
โ”œโ”€โ”€ CLAUDE.md         # Team rules (committed)
โ”œโ”€โ”€ .claude/          # Local hooks only
โ”‚   โ””โ”€โ”€ settings.json # Hooks configuration
โ”œโ”€โ”€ .quaestor/        # Shared documentation (committed)
โ”‚   โ”œโ”€โ”€ QUAESTOR_CLAUDE.md
โ”‚   โ”œโ”€โ”€ CRITICAL_RULES.md
โ”‚   โ”œโ”€โ”€ ARCHITECTURE.md
โ”‚   โ”œโ”€โ”€ MEMORY.md
โ”‚   โ”œโ”€โ”€ PATTERNS.md
โ”‚   โ”œโ”€โ”€ VALIDATION.md
โ”‚   โ”œโ”€โ”€ AUTOMATION.md
โ”‚   โ””โ”€โ”€ manifest.json
โ”œโ”€โ”€ ~/.claude/commands/  # Global commands
โ”‚   โ”œโ”€โ”€ task.md
โ”‚   โ”œโ”€โ”€ status.md
โ”‚   โ”œโ”€โ”€ analyze.md
โ”‚   โ”œโ”€โ”€ milestone.md
โ”‚   โ”œโ”€โ”€ check.md
โ”‚   โ”œโ”€โ”€ auto-commit.md
โ”‚   โ”œโ”€โ”€ milestone-pr.md
โ”‚   โ””โ”€โ”€ project-init.md
โ””โ”€โ”€ .gitignore        # Auto-updated

Now Claude can use commands with project-specific behavior:

/task: implement user authentication
/status
/configure

Installation

# No install needed (recommended)
uvx quaestor init

# Or install globally
pip install quaestor

Commands

CLI Commands:

  • quaestor init - Initialize with smart defaults
    • --mode personal (default) - Local, self-contained setup
    • --mode team - Shared commands and rules
    • --contextual (default) - Analyze project complexity
  • quaestor configure - Customize command behavior
    • --init - Create command configuration
    • --command <name> --create-override - Override specific commands
  • quaestor update - Update while preserving your changes

AI Assistant Commands:

  • /task - Implement features with orchestration
  • /status - Show progress with velocity tracking
  • /analyze - Code analysis across multiple dimensions
  • /milestone - Manage phases with completion detection
  • /check - Quality validation and fixing
  • /auto-commit - Conventional commits for TODOs
  • /milestone-pr - Automated PR creation
  • /project-init - Framework detection and project setup

Key Features

๐Ÿง  Context-Aware Commands

Quaestor commands use patterns for better Claude integration:

  • Auto-activation โ†’ Context-aware triggers and thresholds
  • Performance profiling โ†’ Standard, optimization, and complex execution modes
  • Quality gates โ†’ Error fixing with parallel agents
  • Token efficiency โ†’ Reduction through symbol system

Rules work ambiently in CLAUDE.md, not just in commands!

โš™๏ธ Command Customization

Configure commands per project with .quaestor/command-config.yaml:

commands:
  task:
    enforcement: strict
    parameters:
      minimum_test_coverage: 90
      max_function_lines: 30
    custom_rules:
      - "All APIs must have OpenAPI specs"
      - "Database changes require migrations"

Or create full overrides in .quaestor/commands/task.md.

๐ŸŽฏ Flexible Modes

Installation modes determine where files are stored:

Personal Mode (Default):

  • Everything local in .claude/
  • Perfect for solo developers
  • Commands and context in one place
  • Fully gitignored

Team Mode:

  • Shared standards in .quaestor/
  • Global commands in ~/.claude/
  • Consistent across team
  • Version controlled rules

Note: Both modes support all command complexity levels. Mode choice is about file organization, not project complexity.

๐Ÿ“Š Smart Project Analysis

  • Auto-detects language (Python, Rust, JS/TS, Go, Java, etc.)
  • Identifies test frameworks and CI/CD
  • Recognizes team markers (CODEOWNERS, PR templates)
  • Calculates complexity score

๐Ÿ”„ Workflow Orchestration

Adaptive workflow based on scope:

  • Direct execution: <10 files โ†’ Read + Edit operations
  • Parallel agents: 10-50 files โ†’ Multi-agent coordination
  • Complex systems: >50 files โ†’ Systematic agent delegation
  • Quality cycles: Execute โ†’ Validate โ†’ Fix โ†’ Complete
  • Auto-escalation: Complexity threshold triggers

๐Ÿ“ˆ Command Complexity Thresholds

Commands adapt their behavior based on task complexity (0.0-1.0):

  • Standard (0.2-0.4): Quick, focused operations (e.g., /status, /milestone)
  • Optimization (0.4-0.6): Balanced efficiency with smart features (e.g., /check)
  • Complex (0.6-0.8): Full orchestration and deep analysis (e.g., /task, /analyze)

Thresholds control: auto-activation features, parallel processing, quality gates, and error recovery.

Recent Updates (v0.4.2)

  • Enhanced Hooks System - Comprehensive fixes for better workflow automation
  • Improved Testing - Full test coverage for critical components
  • A1 Development - Working on next-generation automatic intelligence system
  • Documentation Updates - Clearer guidance and updated examples

How It Works

  1. Project Analysis - Scans for language, tests, complexity
  2. Context Generation - Creates appropriate CLAUDE.md rules
  3. Command Setup - Installs commands (local or global)
  4. Customization - Allows per-project overrides
  5. Smart Updates - Preserves your changes

Example Workflows

  • Simple tasks: Direct implementation with quality validation
  • Complex tasks: Orchestrated workflow with parallel agents and quality gates
  • Auto-tracking: Progress updates and conventional commits

Command Customization

quaestor configure --init  # Create config

Edit .quaestor/command-config.yaml to add project-specific rules and enforcement levels.

Ambient Rule Enforcement

Quaestor's rules work everywhere in CLAUDE.md, not just in commands. Rules guide Claude's behavior for complexity checking, delegation triggers, and quality standards across all interactions.

Updating

# Check what would change
quaestor update --check

# Update with backup
quaestor update --backup

# Force update all files
quaestor update --force

Updates preserve your customizations in user-editable files.

What's Coming Next

We're working on A1 (Automatic Intelligence), a next-generation system that will bring:

  • Event-driven architecture for improved performance
  • Enhanced learning and adaptation capabilities
  • Simplified codebase with modular extensions
  • Advanced pattern recognition and workflow detection

A1 is currently in development and not yet ready for production use.

Contributing

git clone https://github.com/jeanluciano/quaestor.git
cd quaestor
uv sync
uv run pytest

License

MIT License


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

quaestor-0.4.2.tar.gz (115.9 kB view details)

Uploaded Source

Built Distribution

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

quaestor-0.4.2-py3-none-any.whl (133.3 kB view details)

Uploaded Python 3

File details

Details for the file quaestor-0.4.2.tar.gz.

File metadata

  • Download URL: quaestor-0.4.2.tar.gz
  • Upload date:
  • Size: 115.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for quaestor-0.4.2.tar.gz
Algorithm Hash digest
SHA256 3d3e9febe347e65604db93c2f4f869549ed1c96ba72c3dab891341db53de892a
MD5 640c22941f4c6721a59eddd861cd723b
BLAKE2b-256 71ed627248008b688d45ae9aca4b8124852acbab8c9b1f0b2785be100dd00e10

See more details on using hashes here.

Provenance

The following attestation bundles were made for quaestor-0.4.2.tar.gz:

Publisher: publish.yml on jeanluciano/quaestor

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file quaestor-0.4.2-py3-none-any.whl.

File metadata

  • Download URL: quaestor-0.4.2-py3-none-any.whl
  • Upload date:
  • Size: 133.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for quaestor-0.4.2-py3-none-any.whl
Algorithm Hash digest
SHA256 9669af7f165917c924a9bc78f6d003e5fc14714d7a581043cca33278d8d7d360
MD5 c90fb3b83543b6075316cb36f3f6f291
BLAKE2b-256 23a65558ab1d685db05971ff4081fd74c0b1d00fc616a2cd5ba6d29b32931f9f

See more details on using hashes here.

Provenance

The following attestation bundles were made for quaestor-0.4.2-py3-none-any.whl:

Publisher: publish.yml on jeanluciano/quaestor

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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