Skip to main content
Get listed

Plandex

Featured

Open-source AI coding agent for large projects — terminal-based agent that plans and executes multi-file changes

AgentsFree

Plandex is an open-source, terminal-based AI coding agent built for large, real-world coding tasks. Unlike in-editor assistants that work one file at a time, Plandex manages entire projects — breaking complex tasks into steps, tracking changes across multiple files, and working through bugs and compilation errors iteratively until the task is complete. It uses a protected sandbox for changes, giving you control to review and apply work incrementally. Available as a hosted cloud service or fully self-hosted.

This tool appears to be discontinued. plandex.ai no longer resolves (checked 2026-11-12).

Key specs
15,908 GitHub stars source
as of 2026-11-12

What we know

LicenseMITsource, checked 2026-11-14
Open sourceYessource, checked 2026-11-14
PricingFreefrom our original listing, not yet re-checked
GitHub stars15,915source, checked 2026-11-14

Why it matters

  • Designed for long, multi-step tasks that in-editor assistants can't complete — Plandex works through an entire feature or refactor from start to finish, not just the next few lines.
  • Protected sandbox for reviewing changes before applying prevents unwanted modifications — you stay in control of what actually goes into your codebase.
  • Terminal-native workflow integrates with existing developer tooling — works anywhere you have a terminal, no IDE required.
  • Self-hostable with MIT license — run the entire agent infrastructure on your own servers for privacy and cost control.

Key capabilities

  • Multi-file planning: Breaks complex tasks into steps across multiple files with a coherent overall plan.
  • Iterative error correction: Catches build errors and test failures; automatically corrects and retries.
  • Sandbox staging: Changes are accumulated in a protected staging area for review before applying.
  • Context management: Intelligently loads relevant files without exceeding context window limits.
  • Terminal-based: Works in any terminal; no IDE extension required.
  • Multiple LLMs: Supports OpenAI GPT, Claude, and other compatible models.
  • Self-hostable: Run Plandex server on your own infrastructure (MIT license).
  • Cloud hosted: Plandex Cloud for zero-infrastructure setup with usage-based pricing.
  • Project memory: Maintains context about what has been built across sessions.

Technical notes

  • License: MIT
  • GitHub: github.com/plandex-ai/plandex
  • Stars: 15K+
  • Interface: CLI (terminal)
  • LLM backends: OpenAI, Anthropic Claude, and compatible APIs
  • Install: curl -sL https://plandex.ai/install.sh | bash
  • Self-host: Docker-based server; or use Plandex Cloud
  • Founded: 2024

Usage example

# Install Plandex
curl -sL https://plandex.ai/install.sh | bash

# In your project directory
plandex new  # Start a new plan
plandex tell "Add a REST API endpoint for user authentication with JWT tokens"
# Plandex plans and implements across multiple files
plandex changes  # Review staged changes
plandex apply    # Apply to codebase

Ideal for

  • Developers tackling large, multi-file tasks that require iterative implementation and error correction.
  • Teams who want a terminal-native AI agent that fits into existing CLI-based workflows.
  • Organizations that want full control over agent infrastructure via self-hosting.

Not ideal for

  • Simple, single-file edits — in-editor AI (Cursor, Copilot) is faster for small changes.
  • Teams who prefer GUI-based agent interactions — Plandex is terminal-only.
  • Tasks requiring real-time collaboration on shared codebases — Plandex works on local file systems.

See also

  • Aider — Similar terminal-based AI coding agent; larger community (60K+ stars); desktop GUI available.
  • GPT-Engineer — Spec-to-codebase agent focused on greenfield project generation.
  • Devika — Open-source AI software engineer with web-based interface; Devin alternative.

FAQ

What is Plandex?

Plandex is an open-source AI coding agent you run from the terminal. You describe a task in natural language (add a feature, fix a bug, refactor a module), and Plandex plans the work, makes changes across multiple files, runs into build errors, corrects them, and iterates until it's done. Changes are staged in a protected sandbox so you can review them before applying to your actual codebase. It's designed for multi-step tasks that require more than a single file change.

Is Plandex free?

The Plandex CLI and server are MIT-licensed and free to self-host. Plandex Cloud (the hosted version) has a free tier with trial credits, then charges based on API usage. Since Plandex uses OpenAI, Anthropic, or other LLM APIs under the hood, you pay for the underlying model API calls. Self-hosting Plandex means you only pay for LLM API costs, with no Plandex platform fee.

How does Plandex handle large codebases?

Plandex manages context carefully for large projects. It loads only the files relevant to the current task, uses a context window manager to stay within model limits, and maintains a project-level memory of what has been built so far. When a task requires changes across many files, Plandex breaks it into sub-tasks and executes them in sequence — tracking the overall plan while handling implementation details per file.

How does Plandex compare to Aider or other AI coding agents?

Aider is also a terminal-based AI coding agent with a large community (60K+ stars). Both support multi-file editing with LLM backends. Plandex emphasizes its sandbox/staging system for reviewing changes before applying them, and its ability to handle very long multi-step tasks with iterative error correction. Aider has more model flexibility and a larger community. The choice often comes down to workflow preference — Plandex's sandbox vs. Aider's more immediate apply pattern.

Alternatives

Is your tool an alternative to Plandex? Sponsor this spot for 30 days, marked Sponsored.

Integrations

None listed.

Built on

None listed.

Related tools

Listed 2026-02-22 · updated 2026-11-12