MeowKitEnforced discipline for AI coding agents

Hard gates, TDD, security scanning, and human approval — so your AI agent ships production-quality code, not untested prototypes.

Get Started →

Why MeowKit

🔒 Two Hard Gates

No code ships without an approved plan (Gate 1) and a passing review (Gate 2). The agent cannot self-approve.

🧪 TDD Enforced

Failing tests must exist before implementation begins. No exceptions. Pre-implement hook blocks code without tests.

🛡️ 4-Layer Security

Prompt injection defense across input boundary, instruction anchoring, context isolation, and output validation.

🧠 13 Specialist Agents

Each agent owns a specific concern — planning, testing, reviewing, shipping. No two agents modify the same files.

⚡ 40+ Skills

From docs retrieval to multimodal analysis, code review to QA testing. Progressive disclosure keeps context tight.

💾 Cross-Session Memory

Lessons, patterns, and costs persist across sessions. After 10 sessions, the analyst proposes CLAUDE.md improvements.

📋 Structured Task System

Template-driven task files help agents resume work without losing context. Five template types with acceptance criteria, constraints, and live agent state tracking.