Speclint
Speclint is an open-source spec linter that scores user stories and requirements on a 0-100 scale across 5 dimensions: Measurable Outcomes (20pts), Testable Criteria (25pts),
Speclint scores your specs 0-100 across 5 dimensions before any AI agent touches them. Deterministic regex scoring — no AI hallucination in the diagnosis. CLI, GitHub Action, and MCP Server.
- Score user stories before handing them to AI coding agents
- Add spec quality gates to CI/CD pipelines
- Rewrite vague requirements into agent-ready specs
- Audit backlog quality across a sprint
- Run npx speclint lint in your terminal
- paste a user story
- and get a 0-100 score instantly. Or add the GitHub Action to score specs on every PR. Or connect the MCP Server to Claude
- Cursor
- or any AI coding agent — it auto-lints specs before the agent writes code.
Approve AI agent data access with Face ID
Clone any website into clean code. Free & open source
Control every aspect of model training and fine-tuning
Caps Lock keeps your Mac awake, even with the lid closed
Screen recordings that edit themselves
The Web Data API for AI Agents and Developers
Find & fix live vulnerabilities in Vibe Apps with 1-prompt.
The easiest way to deploy a managed agent.
See it once. Ask forever.
Platform for building with Google's Gemini AI models.
A modern, visual file manager for the terminal
The AI database client for Mac
Annotate anything for humans and their agents
The terminal and Mac menu bar companion for Kickbacks.ai
A private data-usage meter for your Mac menu bar
API integration testing that remembers what breaks
Manage your team of AI agents by voice, from anywhere
Catch API drift before your customers do
