A configuration layer for existing AI coding agents, adding persistent memory, a development workflow and optional bounded review.
Project overview
It combines accumulated project memory, lightweight or documented task progression, and review receipts tied to the reviewed version.
Project type
AI Agent · AI Coding
Use cases
Coding & Development
Deployment
Refer to project documentation
License
MIT
Best for
Users of existing coding agents who want persistent context and a common development/review workflow.
Key capabilities
Agent writes down what it learns as it goes and retrieves it before asking the user, so project context accumulates across sessions
Keeps understood small changes lightweight and gives substantial authorized work one recoverable feature document, with test-first by default
On-by-default, opt-out bounded review that freezes the candidate before reading it and returns evidence bound to that exact version
Limitations and risks
Each integration uses that agent's native capabilities, so features such as delegation and RDD review can differ per agent
Getting started
brew install gentleman-programming/tap/gentle-ai; gentle-ai; gentle-ai doctor
Evidence and sources
GitHub project description: Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills…
README: Your agent writes code, then forgets everything.
README: your agent writes down what it learns as it goes and reaches for it before it reaches for you, so context accumulates instead of resetting.
README: Organic Driven Development (ODD) keeps understood changes lightweight and gives substantial, authorized work one recoverable feature document.
README: ODD applies test-first development by default when a relevant runnable test and a clear expected outcome exist: capture a failing behavior test before implementation, make it pass…