Explore

Take your agent-built product live: hosting, database, domain, email, payments — on your own accounts. Open-source Agent Skill + zero-dependency Node CLI: detect → plan → approve → apply → verify. No

Skill·MIT·★ 1.3k·No key

The provider's own price, right inside your chat. Make video, images and voice with 400+ Vercel AI Gateway models (Veo, Kling, Seedance, Nano Banana, GPT Image) from Claude, ChatGPT or any MCP app. Yo

Hosted by author·MIT·Few stars·No key

Sponson turns a release's side effects into a file an agent can read and a human can diff.

Skill·Apache-2.0·Few stars·No key

Independent domain operators: signed domains.*@v1 quotes, fixed markup, registration, renewal and DNS. Openprovider, Porkbun Sandbox or HTTP suppliers; x402 USDC on Base and a buyer-side Vercel connec

Hosted by author·MIT·Few stars·No key

Securealy: launch grader, checks, CLI, MCP server and Claude Code plugin for apps built with AI

Node.js·Apache-2.0·Few stars·No key

Jev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.

Node.js·MIT·★ 105·No key

Jev, TypeSafe's System One classifier, as a tool inside Claude Code, Codex, Pi, and OpenCode: typed classify, check, score, rank, and ask, plus one-command setup.

Node.js·MIT·★ 49·No key

Claude skills for UI that doesn't look AI-generated: 16 section layouts with wireframes, section → layout map, anti-AI typography, CSS + R3F recipes, plus find-skills

Skill·MIT·★ 1·Few stars·No key

Jev-powered MCP tool routing for Codex

Skill·MIT·★ 9·No key

A measured tool-call firewall for AI agents: allow, ask or deny before the agent acts. Claude Code mod and hook, MCP proxy. Built on TypeSafe Jev, measured on real sessions with a blind second labeler

Node.js·MIT·★ 25·No key

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to th

Node.js·MIT·★ 62·No key

Know what your stack will cost before the bill arrives. Free agent skill for Claude Code, Cursor and Codex: prices every service at your usage, finds the bills, limits and compliance gaps ahead, each

Skill·MIT·★ 15·No key

Lint Jev and Luna questions: a VS Code extension, a command line for CI and an MCP server, for TypeSafe's Jev and OpenAI's Decisions API

Node.js·MIT·★ 1·Few stars·No key

MCP server + A2A agent: free AI-readiness audit of any URL (AI crawler rules, JS-free text, JSON-LD, llms.txt). Stateless Vercel functions.

Hosted by author·MIT·Few stars·No key

What your last session knew, scored against what this one is doing. MCP server: a per-project ledger written as things happen, recalled per task with TypeSafe's Jev evaluation model via Vercel AI Gate

Node.js·MIT·★ 2·Few stars·No key

Semantic code review with Jev, plain-English rules and Agent Skills.

Skill·MIT·★ 5·No key

Modern React Guidance — authoritative agent skill for React 19+ (Actions, use, Compiler, View Transitions, Fragment refs, Activity, browser(), useEffectEvent). Optimized for AI coding agents.

Skill·MIT·★ 47·No key

Hosted by author·MIT·Few stars·No key

Fine-tuned automation for everyone: visual workflows where AI coding agents act on your tickets, errors and schedules, and ask before they change anything. Works with Claude Code, Codex, OpenCode, Git

Skill·MIT·★ 50·No key

Find agent skills by meaning, not keywords. Local semantic search over shared SKILL.md repos for Claude Code, Codex and OpenCode, as an MCP server. Add any number of skills without growing your agent'

Node.js·MIT·Few stars·No key

See which .env, .git, keys and source maps Cloudflare Pages, Vercel, Netlify or Firebase would publish — before your agent deploys, and after it's live. CLI + live probe + Claude Code hook + MCP + Git

Node.js·MIT·Few stars·No key

Pause and safely resume Browser Use tasks at CAPTCHA: same-session detection, authorized handoff/test actions, and fresh validation. Local MCP + SDK.

Node.js·MIT·★ 1·Few stars·No key