AI Community Directory

is a free directory of AI agent use cases for one-person and small businesses. Answer 5 quick taps and get a plan for your AI team, starting with a morning brief. Browse guides by trade and copy-ready routines for Grok Bot, ChatGPT, Claude or n8n. Every setup is drafts-first, so you approve everything.

is a free, MIT-licensed open-source alternative to Grok Bot for Windows, built with Electron, React, TypeScript, and the Cursor SDK. It lets developers run teams of AI agents with separate models, persistent instructions, workspaces, MCP integrations, long-term memory, and scheduled routines. Agents can exchange stored messages, stream responses, and update their own configuration under locally controlled settings. It is designed for technical users who want inspectable source code and a configurable desktop environment rather than a limited chat interface.

helps admins run WhatsApp groups and communities at scale. It moderates automatically with anti-spam and anti-link rules, welcomes new members, schedules messages and polls, manages participants and warnings, and delivers analytics and weekly summaries. 9bot also offers a remote MCP server so AI assistants like Claude, Cursor and Gemini can manage groups through natural language.

When Claude Code, Codex, Cursor or another AI coding agent works on your laptop, it can run terminal commands, call MCP tools, open files that hold keys and tokens, and pull in new packages. HOL Guard is a local-first runtime layer that runs on your own machine and looks at each of those actions before it happens. You write the policy: allow it, block it, or pause and ask you first. Decisions are kept in a local log you can review later. HOL Guard is not a network gateway or firewall, it is not a complete answer to prompt injection, and its scans are not a guarantee of safety. The core is Apache-2.0 open source

(jevai.website) is a decision-focused AI API and browser playground that returns typed outputs rather than free-form text. Developers can define yes/no checks, fixed-choice classifications, and custom scoring scales over shared text or JSON state, then receive probabilities and confidence information for each result. It is designed for high-volume operational decisions such as ticket routing, risk gates, moderation, and model selection. With a free playground, API access, and credits that do not expire, Optio helps teams add predictable AI branching logic without parsing chat-model responses.

is a free AI speech recognition workspace that converts local audio and video files into editable transcripts and timed subtitles using OpenAI's Whisper model. Processing runs in the browser, keeping selected recordings and transcripts on the user's device rather than sending them to a cloud transcription service. It supports common media formats and exports TXT, SRT, and VTT files, making it useful for creators, researchers, journalists, and editors who need privacy-conscious transcription. Users can choose Whisper model sizes, review timestamps, edit text, and create captions without creating an account.

Sesshu is an AI video generator for creating short videos from text prompts, uploaded images, and character or product references. It supports social-first vertical clips, cinematic scenes, anime-style animation, e-commerce product videos, and game-character trailers through a credit-based generation workflow. Users can specify formats, duration, visual direction, camera movement, and audio settings, with multiple video models available for different styles. It is designed for creators and marketing teams that need polished video assets without filming or conventional animation production.

is an AI styling preview tool that lets shoppers combine separate clothing and accessory product images on a personal full-body photo or an approximate model. It is designed for evaluating outfit cohesion, colour combinations and overall style direction across tops, bottoms, shoes and selected accessories. The service helps online shoppers, fashion-conscious users and stylists reduce uncertainty before checkout or an event, while clearly positioning results as visual styling previews rather than fit or size recommendations. Users receive five one-time free image credits with a verified account, while paid credits and plans support continued image generation and optional runway-style video previews.

is a creative toolkit for AI agents. Connect ChatGPT, Claude, Cursor or any MCP client with one URL to generate AI video (Veo 3.1, Kling 3, Seedance 2.5), clip long videos into captioned shorts, create thumbnails and AI influencers, upscale to 4K, and schedule posts to YouTube, TikTok, Instagram, Facebook and LinkedIn. Also available as a web app and REST API.

is a browser-based live voice translator for 60+ languages. Talk face-to-face on one phone or run multilingual video meetings. No app or hardware needed. Free plan; paid plans from $4/month.

for AI assistants, applications, IVR and recorded voiceovers. It supports streaming through an API and consent-based custom voices. Deployment options include shared cloud, customer cloud and on-premises. Developed by NextGen Speech AI, LLC. Pricing and access are available on request; no public free plan is advertised.

platform that helps academics and research teams turn papers, questions, and datasets into publication- and presentation-ready outputs. It searches and synthesizes full research papers, creates citation-backed literature reviews, analyzes CSV and XLSX files, and generates editable scientific figures. Researchers can also convert papers into academic posters, slide decks, and typeset documents while keeping claims traceable to sources. Built with privacy in mind, Yila is designed for workflows spanning early literature discovery through conference and lab presentations.