MakerChecker
Scan your AI agents for dangerous capabilities
Discover real builders, real businesses
Discover new products, see which launches people talk about, and learn how real businesses make money.
4,964 businesses to explore
Recently listed first · listing date does not establish launch date
Scan your AI agents for dangerous capabilities
AI-native, GPU-accelerated terminal emulator for Windows with SSH, persistent sessions, split panes, and first-class AI
Study what already works, then find the audience, workflow or language nobody is serving yet.
Vibe-Research:A 股、美股、港股的投研工作台 · 自选与持仓、每日复盘、产业资讯、产业研究、个股深挖、回测、研报库,168 个数据端点。支持 Claude Code、Codex、WorkBuddy 订阅或任意模型 API。 |
OpenAI Codex 桌面端/CLI 的可视化管理工具,具有Provider/API 切换、会话同步、提示词注入、Skills/MCP 管理、TOML 配置可视化的跨平台工具。
Wireshark for MCP (transparent proxy and live TUI)
The open-source AI workbench for scientific research
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding spec
The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop a
autonomous red teaming platform; multi-agent offensive-security meta-harness
Search the coding agent history already on your machine
Manufact, a YC S25 company
CLI tool for detecting non-exact code duplication with embedding models
I built an open-source alternative to Claude Cowork
Self-learning agent browser
Claudoro, Pomodoro timer embedded in the Claude Code statusline
把 Markdown 一键排成可直接粘进公众号编辑器的精致 HTML —— 6 套精选主题 + 主题生成器 + 双关卡校验。An AI-agent skill that turns Markdown into paste-ready WeC
Local-first search engine and MCP server for AI agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for
Open-source auth gateway connecting 1500+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI.
A lightweight, dependency-free Bash wrapper for LLM APIs
GPT-2 scale model in pure C/CUDA from scratch
Versioned Codex instruction deployment with preview, ownership manifests, hook isolation, scenario evaluation, and recov
keep a lid-closed Mac awake only while agents work
Smart model routing directly in Claude, Codex and Cursor
Agents that test web and mobile apps