# plandex-ai/plandex

Open source AI coding agent. Designed for large projects and real world tasks.

Repository: https://github.com/plandex-ai/plandex
Canonical: https://ross.abutalabs.com/products/plandex
Homepage: https://plandex.ai
Language: Go
License: MIT
License Family: permissive
Topics: ai, ai-developer-tools, gpt-4, llm, openai, ai-agents, ai-tools, cli, developer-tools, polyglot-programming, terminal-based, golang, git, terminal, terminal-ui, command-line
Last push: 2025-10-03T21:49:58+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 45, release rhythm 40, longevity 74
- inputs: {"age_days": 1044, "days_push": 334, "days_rel": 413, "gap_med": 0.0, "n_releases_24m": 47}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 15597, forks 1177 (observed 2026-08-28T04:11:12.607932+00:00)

## What it is
Plandex is an open-source, terminal-based AI coding agent that plans and executes large, multi-step coding tasks across many files in real-world projects. It supports large context windows, tree-sitter project maps for indexing big codebases, and a diff review sandbox that keeps AI changes isolated until approved.

## Use cases
- refactor code across dozens of files with an AI agent
- have an AI plan and implement a multi-step feature in my repo
- review AI-generated diffs before applying them to my project
- work on a large codebase with an AI coding assistant in the terminal
- self-host an AI coding agent for my team
- let an AI fix bugs across a real-world project

## When to choose
- you need an AI agent that handles large, multi-file tasks with big context windows
- you prefer a terminal-based workflow with git integration
- you want AI changes sandboxed and reviewed before applying
- you want a self-hostable, MIT-licensed coding agent

## When to avoid
- you only need simple single-file autocomplete or inline completions
- you want a GUI or IDE plugin experience
- you don't want to rely on LLM API access or costs

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, llm-inference, developer-tools, cli, terminal-ui
- domain: developer-tools, artificial-intelligence, large-language-models
- platform: cli, windows, cross-platform
- tags: ai-coding-agent, code-generation, git-integration, golang, self-hosted, openai, ai-agents, command-line, linux, macos

## Member repositories
- plandex-ai/plandex (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:12.607932+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:05:38.076637+00:00, confidence not recorded.
  - readme: https://github.com/plandex-ai/plandex (fetched 2026-08-28T04:11:12.607932+00:00, sha 9e62278d63d7)
- Data as of 2026-08-30T08:39:29.467469+00:00.