Private, local-first AI coding agent with approval-based automation
Atlarix is a desktop and terminal AI coding agent for teams that can plan changes, edit repositories, run commands and tests, and review pull requests. It keeps code on your machine, supports cloud-provider keys and local models, and requires approval before file changes are applied.
Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric → Last re-evaluated 7 October 2026.
Ask about Atlarix
Get answers based on Atlarix's actual documentation
Try asking:
About
Atlarix is a private AI coding agent for engineering teams, delivered as a desktop application for macOS, Windows, and Linux, plus a terminal CLI, Chrome extension, GitHub pull-request reviewer, and a cloud agent for GitHub Actions. It is designed...
Atlarix is meaningfully agentic rather than a code-completion tool: it can work through multi-step engineering tasks, run a persistent shell, check failed commands or unapplied edits, and split work into up to five parallel efforts. Its strongest...
Handles domain-specific workflows independently with dynamic replanning.
Dimension Breakdown
Categories
Ask about Atlarix
Try asking:
- Free: Includes every feature, Atlarix Auto in the desktop app (with a one-time consent for prompts to be shared with OpenAI), bring-your-own API keys, and local models.
- Pro ($19/mo): Includes Atlarix Core model usage and Atlarix Reviewer for unlimited repositories and pull requests.
- Usage-based: Pay-as-you-go credit for Core models starts at $10.
When Atlarix changes its pricing, we catch it the next morning
We recrawl every tool in this directory daily. AI Insider is the 3-minute brief on what actually changed — pricing, features, score moves on our 36-point rubric — often before any press coverage. Sent daily. Skipped when nothing happened.