realmyang/MLView

Interactive, source-linked ML workflow diagrams written by your coding assistant (Copilot, Codex or Claude Code) and opened in VS Code.

What it solves

MLView helps developers understand complex machine learning workflows by transforming source code and configuration files into interactive, visual diagrams. It addresses the difficulty of manually tracing how data, models, and training parameters interact within a codebase.

How it works

MLView provides a skill for AI assistants like GitHub Copilot, Codex, and Claude Code. When prompted, the assistant reads your project files and generates a structured JSON file representing the workflow. You can then open this file in VS Code using the MLView extension, which renders an interactive diagram. The tool allows you to click on diagram elements to view the specific lines of code that support each claim, and you can ask the assistant to refine the diagram iteratively.

Who it’s for

It is designed for developers and data scientists working in VS Code who need to visualize, audit, or explain machine learning training pipelines and configurations to themselves or their team.

Highlights

  • Generates interactive, source-linked diagrams directly from your existing ML code and configuration.
  • Supports iterative refinement, allowing you to ask your AI assistant to update or clarify specific parts of the diagram.
  • Enables bidirectional navigation: click diagram nodes to jump to source code, or right-click code to reveal its corresponding step in the diagram.
  • Includes a review mode to walk through claims, highlighting cited code lines for verification.
  • Provides a "Phase overview" to visualize the entire workflow structure, including branches, cycles, and nested groups.

Related

  • Project
    boshu2/agentops

    A DevOps discipline for AI coding agents that provides structured workflows, BDD-based planning, and persistent memory to make agentic software delivery repeatable and reliable.

  • Project
    kaanozhan/Frame

    Frame is an Electron‑based desktop IDE that adds a persistent, git‑tracked “project memory” for AI coding assistants (Claude Code, Codex, Gemini). It creates a `.frame/` folder with rules, architecture maps, task lists and a spec‑driven workflow, injects this context into each AI session, and anchors updates to git commits via pre‑commit hooks. Features include a multi‑terminal grid, task/spec panels, GitHub integration, fast file lookup, and multi‑AI switching. Intended for developers who want reliable, shareable context when working with LLM‑powered agents.

  • Project
    GMaN1911/claude-cognitive

    Claude Cognitive adds persistent working memory to Claude Code, using a context router that scores and injects files based on attention and a pool coordinator that shares state across multiple instances, cutting token usage and preventing duplicate work.

  • Project
    mlhher/late-cli

    Late is an AI coding agent that prevents context degradation by delegating tasks to ephemeral subagents, ensuring the primary orchestrator remains focused and efficient during long, complex workflows.