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.
Sync your mailbox with your issue tracker
Instant, hardware Isolated Sandboxes for AI agents
Scale PostgreSQL without changing your app
Catch API drift before your customers do
Fastest LLM runtime on Apple Silicon
A free, open source, Descript alternative. Runs in-browser.
Comment on your AI agent's code & collaborate on changes
Annotate anything for humans and their agents
The web performance & security company
Manage your team of AI agents by voice, from anywhere
Screen recordings that edit themselves
API integration testing that remembers what breaks
A modern, visual file manager for the terminal
The terminal and Mac menu bar companion for Kickbacks.ai
A private data-usage meter for your Mac menu bar
Platform for building with Google's Gemini AI models.
Caps Lock keeps your Mac awake, even with the lid closed
Your time travel debugger
