Specmint
Spec-driven development for AI coding agents with persistent, resumable specs
Visit specmint.io ↗What is Specmint?
Specmint replaces ephemeral AI coding plans with durable specifications built through deep research and iterative interviews. It works with Claude Code, Cursor, Codex, Windsurf, Cline, Gemini CLI, and other AI coding tools as a universal skill. Users can pause mid-implementation, switch between multiple specs, and resume exactly where they left off days later.
The workflow follows four disciplined phases: exhaustive codebase analysis and web research, targeted architecture questions, structured spec generation with decision logs, and task-by-task implementation with verification gates. Specs are available in markdown (git-friendly) or rich HTML formats, with optional test-driven development enforcement. The maker says it was built with Claude Code.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Specmint automatically. Evidence: GitHub ngvoicu/specmint-core; repo has AGENTS.md, CLAUDE.md. View source.
Similar vibe-coded apps
#1 this weekOpen-source local voice cloning, dubbing, transcription, and audiobook creation
#2 this week
#5 this weekSlash commands and agents for engineers using AI without compromising standards
#6 this week523 free lessons building AI systems from math and first principles
#8 this week
#10 this weekAI-powered design intelligence toolkit for building professional interfaces

Manage teams of AI agents to run your business from one dashboard

Persistent memory for AI agents across Claude Code, Cursor, and MCP clients