envd

One-Minute Overview#

envd is a command-line tool that helps you create container-based development environments for AI/ML. With complex system dependencies and configurations, envd uses simple declarations (in build.envd files) and a single command (envd up) to quickly set up the exact environment you need, avoiding the headaches of dealing with Python, CUDA, BASH scripts, and Dockerfile changes.

Core Value: Environment configuration as code, making AI/ML development environments standardized, reproducible, and easy to collaborate on.

Getting Started#

Installation Difficulty: Low - Only requires Docker and envd package, can be running in just a few commands

# Install envd
pip install --upgrade envd

# Bootstrap the installation
envd bootstrap

# Clone example project
git clone https://github.com/tensorchord/envd-quick-start.git

# Create environment
cd envd-quick-start && envd up

Is this suitable for me?

• ✅ AI/ML Project Development: Especially suitable for machine learning projects with complex dependencies like CUDA and specific Python packages
• ✅ Team Collaboration: Share environment configurations through build.envd files, avoiding the "it works on my machine" problem
• ✅ Cross-Platform Development: Supports usage from local machines to Kubernetes clusters
• ❌ Simple Web Application Development: May be overkill for regular web apps without complex dependencies

Core Capabilities#

1. Declarative Environment Configuration - Simplified Environment Creation#

• Define your environment needs through Python-style build.envd files, without writing complex Dockerfiles User Value: Lowers the barrier to environment configuration, allowing developers to focus on code rather than environment issues

2. Multi-Language Support - Meeting Different Tech Stack Needs#

• Supports multiple AI/ML programming languages including Python, R, and Julia User Value: Team members with different tech stacks can use a unified tool for managing development environments

3. Environment Isolation & OCI Compatibility - Ensuring Environment Consistency#

• Creates fully isolated container environments that conform to OCI image specifications User Value: Ensures consistency across development, testing, and production environments, avoiding problems caused by environment differences

4. Caching & Accelerated Builds - Improving Efficiency#

• Supports PyPI/APT caching to avoid redownloading packages; supports remote building User Value: Significantly reduces environment build time, especially when dealing with numerous dependencies

5. Knowledge Sharing & Reuse - Promoting Team Collaboration#

• Import environment configuration modules from Git repositories using the include function User Value: Teams can share and reuse environment configurations, avoiding reinventing the wheel

Tech Stack & Integration#

Development Language: Python Main Dependencies: Docker (20.10.0 or above) Integration Method: CLI Tool

Maintenance Status#

• Development Activity: Actively developed with continuous updates and feature enhancements
• Recent Updates: Recent major version updates with new features added
• Community Response: Active Discord community and contributor base

Documentation & Learning Resources#

• Documentation Quality: Comprehensive with detailed usage guides and examples
• Official Documentation: https://envd.tensorchord.io/
• Sample Code: Available for multiple languages and scenarios