AI Tools for Developers
by docker
Agentic AI workflows enabled by Docker containers. It combines Dockerized Tools, Markdown, and the LLM of your choice to create novel workflows.
Last updated: N/A
What is AI Tools for Developers?
A Docker image that enables infinite possibilities for novel workflows by combining Dockerized Tools, Markdown, and the LLM of your choice. It allows you to write complex workflows in markdown files and run them with your own LLM in your editor, terminal, or any environment, thanks to Docker.
How to use AI Tools for Developers?
Use the VSCode extension or the CLI. For VSCode, install the extension, set your OpenAI API key, select a target project, and run the prompt. For CLI, set your OpenAI key, and run the container in your project directory using the provided docker run command.
Key features of AI Tools for Developers
Markdown-based workflows
Dockerized Tools
Conversation Loop
Multi-Model Agents
Project-First Design
Prompts as trackable artifacts
MCP server support
Use cases of AI Tools for Developers
Generating Dockerfiles
Automating software development tasks
Creating multi-agent workflows
Extracting project context
Version controlling prompts
Integrating AI into existing development workflows
FAQ from AI Tools for Developers
What is MCP?
What is MCP?
MCP stands for Model Context Protocol. Prompts and their tools can be used as MCP servers.
How do I register prompts for MCP?
How do I register prompts for MCP?
Use serve mode with the --mcp flag. Then, register prompts via git ref or path with --register <ref>.
Where can I find more documentation?
Where can I find more documentation?
You can find more documentation at https://vonwig.github.io/prompts.docs/
How do I install the VSCode extension?
How do I install the VSCode extension?
Get the latest release from https://github.com/docker/labs-ai-tools-vscode/releases/latest and install with code --install-extension 'labs-ai-tools-vscode-<version>.vsix'
What are Dockerized Tools?
What are Dockerized Tools?
OpenAI API compatible LLM's already support tool calling. These tools could just be Docker images. Some of the benefits using Docker based on our research are enabling the LLM to: take more complex actions, get more context with fewer tokens, work across a wider range of environments, operate in a sandboxed environment