Skip to content
Back to search

labs-ai-tools-for-devs

Your trusted home for discovering MCP tools – seamlessly integrated into Docker

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/docker--labs-ai-tools-for-devs/badge.svg)](/listings/docker--labs-ai-tools-for-devs)

HTML

<a href="/listings/docker--labs-ai-tools-for-devs"><img src="/api/listings/docker--labs-ai-tools-for-devs/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 152 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <!---
  2. ---
  3. tools:
  4. - name: curl
  5. ---
  6. -->
  7. ### :warning: Deprecation Notice: This repository is now deprecated and is no longer under active development. Please use the [integrated MCP Toolkit in Docker Desktop](https://docs.docker.com/go/mcp-toolkit) instead.
  8. **This README is an agentic workflow**
  9. # AI Tools for Developers
  10. Agentic AI workflows enabled by Docker containers.
  11. Just Docker. Just Markdown. BYOLLM.
  12. ## MCP
  13. Any prompts you write and their tools can now be used as [MCP servers](https://www.anthropic.com/news/model-context-protocol)
  14. Use serve mode with `--mcp` flag. Then, register prompts via git ref or path with `--register <ref>`
  15. ```sh
  16. # ...
  17. serve
  18. --mcp
  19. --register github:docker/labs-ai-tools-for-devs?path=prompts/examples/generate_dockerfile.md
  20. --register /Users/ai-overlordz/some/local/prompt.md
  21. # ...
  22. ```
  23. ![overall architecture diagram preview](img1.png)
  24. Source for many experiments in our [LinkedIn newsletter](https://www.linkedin.com/newsletters/docker-labs-genai-7204877599427194882/)
  25. [**VSCode Extension**](https://github.com/docker/labs-ai-tools-vscode)
  26. [**Docs**](https://vonwig.github.io/prompts.docs/)
  27. # What is this?
  28. This is a simple Docker image which enables infinite possibilities for novel workflows by combining Dockerized Tools, Markdown, and the LLM of your choice.
  29. ## Markdown is the language
  30. Humans already speak it. So do LLM's. This software allows you to write complex workflows in a markdown files, and then run them with your own LLM in your editor or terminal...or any environment, thanks to Docker.
  31. ## Dockerized Tools
  32. ![dockerized tools](img4.png)
  33. OpenAI API compatiable LLM's already support tool calling. We believe these tools could just be Docker images. Some of the benefits using Docker based on our [research](https://www.linkedin.com/newsletters/docker-labs-genai-7204877599427194882/) are enabling the LLM to:
  34. - take more complex actions
  35. - get more context with fewer tokens
  36. - work across a wider range of environments
  37. - operate in a sandboxed environment
  38. ## Conversation *Loop*
  39. The conversation loop is the core of each workflow. Tool results, agent responses, and of course, the markdown prompts, are all passed through the loop. If an agent sees an error, it will try running the tool with different parameters, or even different tools until it gets the right result.
  40. ## Multi-Model Agents
  41. Each prompt can be configured to be run with different LLM models, or even different model families. This allows you to use the best tool for the job. When you combine these tools, you can create multi-agent workflows where each agent runs with the model best suited for that task.
  42. With Docker, it is possible to have frontier models plan, while lightweight local models execute.
  43. ## Project-First Design
  44. To get help from an assistant in your software development loop, the only context necessary is the project you are working on.
  45. ### Extracting project context
  46. ![extractor architecture](img2.png)
  47. An extractor is a Docker image that runs against a project and extracts information into a JSON context.
  48. ## Prompts as a trackable artifact
  49. ![prompts as a trackable artifact](img3.png)
  50. Prompts are stored in a git repo and can be versioned, tracked, and shared for anyone to run in their own environment.
  51. # Get Started
  52. We highly recommend using the VSCode extension to get started. It will help you create prompts, and run them with your own LLM.
  53. ## Running your first loop
  54. ### VSCode
  55. **Install Extension**
  56. Get the [latest release](https://github.com/docker/labs-ai-tools-vscode/releases/latest) and install with
  57. ```sh
  58. code --install-extension 'labs-ai-tools-vscode-<version>.vsix'
  59. ```
  60. **Running:**
  61. 1. Open an existing markdown file, or create a new markdown file in VSCode.
  62. > You can even run *this* markdown file directly!
  63. 2. Run command `>Docker AI: Set OpenAI API Key` to set an OpenAI API key, or use a dummy value for local models.
  64. 3. Run command `>Docker AI: Select target project` to select a project to run the prompt against.
  65. 4. Run command `>Docker AI: Run Prompt` to start the conversation loop.
  66. ### CLI
  67. Instructions assume you have a terminal open, and Docker Desktop running.
  68. 1. Set OpenAI key
  69. ```sh
  70. echo $OPENAI_API_KEY > $HOME/.openai-api-key
  71. ```
  72. Note: we assume this file exists, so you must set a dummy value for local models.
  73. 2. Run the container in your project directory
  74. ```sh
  75. docker run
  76. --rm \
  77. --pull=always \
  78. -it \
  79. -v /var/run/docker.sock:/var/run/docker.sock \
  80. --mount type=volume,source=docker-prompts,target=/prompts \
  81. --mount type=bind,source=$HOME/.openai-api-key,target=/root/.openai-api-key \
  82. vonwig/prompts:latest \
  83. run \
  84. --host-dir $PWD \
  85. --user $USER \
  86. --platform "$(uname -o)" \
  87. --prompts "github:docker/labs-githooks?ref=main&path=prompts/git_hooks"
  88. ```
  89. See [docs](https://vonwig.github.io/prompts.docs/#/page/running%20the%20prompt%20engine) for more details on how to run the conversation loop.
  90. ## Building
  91. ```sh
  92. #docker:command=build
  93. docker build -t vonwig/prompts:local -f Dockerfile .
  94. ```
  95. Now, for the agentic workflow...
  96. # prompt system
  97. You are an expert at reading readmes.
  98. Use curl to get the readme for https://github.com/docker/labs-ai-tools-for-devs before answering the following questions.
  99. # prompt user
  100. What is this project?

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.