plandex-ai/plandex

★ 15,360GoAudience · developerComplexity · 3/5Setup · easy

Mindmap

mindmap
  root((plandex))
    What it does
      AI coding agent
      Multi-file task execution
      Sandbox review model
    Key features
      Change sandbox
      Built-in version control
      Model mixing packs
      Autonomous mode
    Supported models
      Anthropic Claude
      OpenAI GPT
      Google Gemini
    Use cases
      Large refactors
      Feature implementation
      Automated debugging

mindmap root((plandex)) What it does AI coding agent Multi-file task execution Sandbox review model Key features Change sandbox Built-in version control Model mixing packs Autonomous mode Supported models Anthropic Claude OpenAI GPT Google Gemini Use cases Large refactors Feature implementation Automated debugging

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Delegate a complex multi-file refactor to an AI agent and review every change before it touches your actual codebase.

USE CASE 2

Run a fully autonomous coding session where the agent plans, implements, executes commands, and debugs a feature end-to-end.

USE CASE 3

Mix models from Anthropic, OpenAI, and Google on a single task using curated model packs to balance cost and quality.

USE CASE 4

Use built-in version control to branch, explore an alternative implementation, and roll back if it doesn't work.

Tech stack

Getting it running

Difficulty · easy Time to first run · 30min

Windows users must use WSL, requires API keys for the AI model providers you choose to use.

In plain English

Plandex is a terminal-based AI coding agent designed for large coding tasks and real-world projects, the kind that span many steps and touch dozens of files. Rather than just suggesting a snippet, it aims to plan and execute substantial pieces of work end-to-end, while keeping you in control. The way it works is built around a sandbox review model. AI-generated changes are kept separate from your actual project files until you decide to apply them, so you can review every modification, roll things back, and debug without leaving a mess behind. Command execution is gated in a similar way. It uses tree-sitter (a code-parsing tool) to build project maps, which lets it stay reliable across large codebases, the README claims an effective context window of around 2 million tokens with its default model pack, and supports indexing directories of 20 million tokens or more. A key idea is that you can mix and combine models from providers like Anthropic, OpenAI, Google, and open source options, using curated "model packs" that trade off capability, cost, and speed. Other features include automated debugging of terminal commands and browser apps, full version control with branches for exploring alternatives, and Git integration with commit-message generation. You would reach for Plandex when other AI coding tools break down on bigger projects, large files, complex refactors, or features touching many files at once. You can run it in fully autonomous mode where it loads files, plans, implements, runs commands, and debugs on its own, or use step-by-step review. It is written in Go, installs with a one-line shell command, and supports Windows only through WSL.

Copy-paste prompts

Prompt 1

Using Plandex, implement a REST API endpoint in my Go project that accepts JSON, validates it, and writes to a Postgres database.

Prompt 2

Have Plandex refactor my entire authentication module to replace JWT tokens with session cookies, touching all relevant files.

Prompt 3

Set up a Plandex autonomous session to add unit tests across my Python project and fix any test failures it discovers.

Prompt 4

Use Plandex to migrate my Express app from CommonJS to ES modules, updating all imports and the package.json config.

Prompt 5

In Plandex, create a feature branch, implement a dark mode toggle in my React app, and show me the full diff before applying.

Open on GitHub → Explain another repo

← plandex-ai on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.