Directory · Skills
Gentle-AI
Configures existing coding agents like Claude Code, Codex, and Cursor with persistent memory, workflows, skills, MCP servers, and review.
★ 7,770 stars · last updated 2026-10-14 · Free, open source · View on GitHub
Best for
- Developers who want persistent project memory across agent sessions
- Teams using multiple coding agents who want one shared configuration layer
- Users wanting a lightweight structured workflow with test-first defaults and risk-based review
Our take
Open source Go tool under MIT that supports 17 agent integrations, including Claude Code, OpenCode, Codex, Cursor, Gemini CLI, and Pi, across macOS, Linux, and Windows. It bundles Engram memory, Organic Driven Development (ODD) for sizing tasks, delegation rules for subagents, and Receipt-Driven Development (RDD) review, which is on by default and can be disabled with `gentle-ai review mode disable`. The README publishes benchmark comparisons, but they are single runs (n=1). The truncated README did not include install commands; it links to a separate quickstart doc.
Similar skills
- Karpathy-Inspired Claude Code Guidelines: A single CLAUDE.md with four principles to curb overengineering, silent assumptions, and unrelated edits in Claude Code.
- Scientific Agent Skills: A library of 177 Agent Skills that guide coding agents through scientific packages, databases, and research workflows.
- reverse-skill: Skill router pack that directs AI coding agents to the right methodology and tools for reverse engineering, pentesting, and security tasks.
- book-to-skill: Converts technical books, document folders, or source collections into structured Agent Skills for Claude Code and other coding agents.
- Hallmark: Design skill for Claude Code, Cursor, and Codex that builds, audits, and redesigns UI while avoiding generic AI-generated looks.
- Claude Skills (alirezarezvani): Large MIT-licensed library of 380+ agent skills, agents, and commands for Claude Code, Codex, Gemini CLI, Cursor, and other coding agents.