Plandex is an open-source, terminal-based AI coding agent designed for large-scale software development across complex, multi-file codebases. It combines autonomous planning, intelligent context discovery, and a sandbox-first workflow to deliver production-grade code changes safely and efficiently.

ai_agent cli coding planning open_source

Plandex is built for developers who need AI assistance on real-world projects with large codebases. Unlike simpler AI coding assistants, Plandex can autonomously handle tasks spanning dozens of files, supporting projects with 20M+ tokens and codebases with millions of lines. It uses a unique plan/apply workflow where all changes accumulate in a version-controlled sandbox before being applied to the project.

• Full Auto Mode – Completes complex tasks autonomously including planning, context loading, implementation, command execution, and auto-debugging
• Multi-File Operations – Updates dozens of files in a single task without manual intervention
• Diff Review Sandbox – All changes accumulate in a version-controlled sandbox before approval
• Sandbox Versioning – Rewind to any previous state or create branches for alternative approaches
• 2M Token Context Window – Indexes projects of 20M+ tokens using tree-sitter project maps across 30+ languages
• Configurable Autonomy – Move between full automation and step-by-step manual control
• Multi-Provider LLM Support – Combines models from Anthropic, OpenAI, Google, and more

Plandex uses a client-server architecture. The server can be self-hosted locally via Docker or accessed through Plandex Cloud. The plan/apply workflow proceeds through distinct phases:

1. Context Discovery – Tree-sitter project maps identify relevant files
2. Planning – AI creates a detailed execution plan
3. Implementation – Each step is executed systematically
4. Change Application – A race orchestration between multiple strategies (deterministic edits, diff edits, whole file builds)
5. Validation – Commands run for dependency installation, builds, and tests
6. Auto-Debugging – Failed commands are automatically debugged

Plandex supports a wide range of model providers through built-in integrations and model packs:

• Anthropic – Claude models
• OpenAI – GPT and o-series models
• Google – Gemini 2.5 Pro/Flash via AI Studio and Vertex AI
• Azure OpenAI – Enterprise deployments
• AWS Bedrock – Managed model access
• DeepSeek – DeepSeek API
• OpenRouter – Aggregated access
• Ollama – Local open-source models
• Perplexity – Search-augmented models

Built-in model packs include gemini-planner, google, and o3-planner for different workflow optimizations.

Plandex can be self-hosted locally with Docker or used via Plandex Cloud:

# Self-hosted local mode with Docker
docker run plandex/plandex
 
# Cloud mode - two tiers available:
# 1. Integrated Models (no API keys needed)
# 2. BYO API Key (use your own accounts)

Configuration is JSON-based with IDE integration support. Model settings (temperature, top-p) are version-controlled, enabling A/B testing across branches.

# Configure models for current plan
plandex set-model
 
# Set default models for new plans
plandex set-model default
 
# Manage custom providers and model packs
plandex models custom
 
# JSON editing mode
plandex set-model --json

• Plandex on GitHub
• Official Website
• Documentation
• Self-Hosting Guide

• openai_codex – OpenAI Codex CLI terminal coding agent
• gptme – Terminal agent with local tools
• Claude Code – Anthropic Claude Code CLI agent
• Warp Terminal – Warp agentic development environment