By Plandex AI

Plandex

Terminal-based open-source AI coding agent for large, multi-file tasks. Maintains a diff sandbox — AI-generated changes stay separate until reviewed. Supports up to 2M tokens of context directly; tree-sitter project maps for larger repos. Works with Anthropic, OpenAI, Google, and local models via Ollama. Cloud service ended October 2025; self-hosted or local mode only.

Filed under AI Coding Agents with AI Coding Assistants. Status: Published

GitHub stats not yet collected ; check back after the next weekly refresh.

On the maker

Plandex AI

Makers of the open-source Plandex terminal AI coding agent (MIT license). Cloud service wound down October 2025; project continues on GitHub under plandex-ai/plandex.

Use cases

Code Generation.

Code GenerationTools that generate, complete, or rewrite source code as their primary output.

Pricing

Free / open-source (MIT)

Field notes

No field notes yet.

Field notes for Plandex will land here when sources support a confident take ; synthesized from postmortems, vendor retros, dev-team blogs, deeply-engaged GitHub issues, and our own builds.

Coverage isn’t promised on every tool ; empty sections are honest. Field notes are curated, not generated from vendor copy.

Benchmarks

Scores aren’t in yet.

We’re wiring up SWE-bench, Aider Polyglot, and a custom dev-task suite next. Methodology will be public; vendor pre-notification is 48 hours.

View benchmarks

How we make money

This directory is supported by display advertising. Advertisers do not influence editorial rankings, benchmark scoring, or which tools are featured. Tools are ordered by data.

Editorial independence policy →