coldteadotai/pr-lens

Review code 100X faster. Lens draws every PR as animated architecture and data-flow walkthroughs, inside the pull request itself. Use it as a GitHub App, GitHub Action, CLI, or a Skill for your coding agent

What it solves

PR Lens addresses the difficulty of understanding complex code changes by automatically generating visual architecture and data-flow diagrams for pull requests. It helps developers grasp the impact of a change—such as which components are modified, added, or removed—without needing to manually parse code diffs.

How it works

PR Lens analyzes code changes and renders them as interactive, animated diagrams. It can be installed as a GitHub App, a GitLab CI/CD component, or a Bitbucket pipe to automatically post these diagrams as comments on pull requests. The tool uses a custom renderer to create diagrams that show system architecture, data flow, and specific payload changes. Developers can also use it via a CLI or integrate it with coding agents to visualize codebases or pending changes before a pull request is even opened.

Who it’s for

This tool is designed for software engineers, code reviewers, and teams working on complex or large-scale codebases who want to accelerate the review process and improve architectural visibility.

Highlights

  • Animated Visualizations: Automatically generates architecture and data-flow diagrams that illustrate code additions, changes, and removals.
  • Interactive Canvas: Provides a full-size, zoomable canvas for exploring diagrams, with support for step-by-step walkthroughs.
  • Agent Integration: Allows coding agents to generate and attach diagrams to pull requests, or to interact with the canvas to answer questions about the code.
  • Multi-Platform Support: Works natively with GitHub, GitLab, and Bitbucket, with configurable settings to refine diagram names and groupings.

Related

  • Project
    hustcer/deepseek-review

    DeepSeek Code Review is a tool (GitHub Action + Nushell CLI) that uses DeepSeek LLMs to automatically review code changes in pull requests, with customizable prompts, model choice, and support for local diff reviews.

  • Project
    The-PR-Agent/pr-agent

    PR‑Agent is an open‑source AI bot that automatically reviews pull‑requests (or issues) using LLMs. It can summarize changes, give a full code‑review, suggest improvements, or answer free‑form questions. The tool works with GitHub, GitLab, Bitbucket, Azure DevOps, and Gitea, and can be run as a GitHub Action, Docker container, or local CLI. Prompts are fully configurable, and it supports many LLM providers via LiteLLM. Self‑hosting keeps data private, and the project is community‑maintained with sponsorship from Qodo.

  • Project
    CodeBoarding/CodeBoarding

    CodeBoarding is an open‑source tool that statically analyses a codebase, clusters the code into high‑level components, uses LLMs to generate readable descriptions, and outputs an `analysis.json` that can be visualised as architecture maps in a web UI, VS Code, or CI. It helps reviewers see the impact of pull‑requests at the component level and can render documentation automatically.

  • Project
    taovc/pr-cockpit

    PR Cockpit is a local desktop application that lets you review, fix, and manage GitHub pull requests using AI, ensuring all code stays on your machine and every action is gated by your approval.

  • Project
    Agent-Field/pr-af

    An open-source agentic code reviewer that performs deep architectural audits using a dynamic pipeline and evidence grounding to find systemic vulnerabilities.