AI Apps Directory

Real-time voice AI: fast TTS and production phone agents.

An enterprise voice-AI platform built on deliberately small, fast speech models. Waves handles text-to-speech, voice cloning, and conversion in 30+ languages, while Atoms is a real-time voice-agent platform that plugs into business systems for support, lead qualification, and outbound calls. The company says it can generate 10 seconds of speech in about 100 milliseconds for sub-second voicebot responsiveness.

One speech AI API for real-time transcription, TTS, and translation.

A multilingual speech platform built on Soniox's own universal recognition model: real-time and async speech-to-text, text-to-speech, and any-to-any speech translation across 60+ languages from a single API. It returns token-level results within milliseconds and keeps transcribing through crosstalk, speaker overlap, and mid-sentence language switches. A consumer app (web and iOS) wraps the same engine for recording, transcription, and notes.

Run and manage containerized MCP servers from Docker Desktop.

Docker's Model Context Protocol stack: a Catalog of 200+ verified, containerized MCP servers (from publishers like Stripe, GitHub, Grafana, MongoDB, and Notion), a Toolkit built into Docker Desktop for one-click install and secret/OAuth management, and an open-source Gateway that proxies many servers behind a single secure endpoint. Each server runs in its own isolated container, so agents in Claude Desktop, Cursor, or VS Code get controlled tool access without hand-editing JSON config.

AI search and reading copilot that lives in your browser.

A browser extension that overlays an AI assistant on any web page: summarize long articles, ask questions about what you're reading, and use Focus to unpack complex terms in place. Its Cross-check feature pulls independent sources on a claim, and Suggestions surfaces related news, academic papers, and videos — so research happens without leaving the tab.

Agentic spreadsheet where every cell runs its own AI agent to research and fill data.

A web-based spreadsheet reimagined as a living workspace powered by swarms of AI agents. Each cell can run its own agent that finds, verifies, and fills in data, so the sheet actively researches, analyzes, and produces deliverables in real time. It's aimed at bulk data gathering and enrichment across consulting, finance, sales, and operations workflows.

AI agent for spreadsheets that builds and edits financial models in Excel and Sheets.

An AI agent purpose-built for spreadsheet work, from cleaning data and writing formulas to building full financial models — DCFs, LBOs, and three-statement models — from a natural-language prompt. It runs as a web app and as native add-ins for Excel and Google Sheets, with a Windows CLI for power users. Built for analysts who live in spreadsheets rather than as a generic chatbot bolted onto a grid.

Alibaba's standalone agentic IDE with project-wide context and a Quest Mode.

An AI-first desktop IDE from Alibaba built around agentic coding rather than autocomplete. It indexes a whole project to reason over dependencies and architecture, offers a conversational Agent Mode for pair programming, and a Quest Mode that takes a written spec, plans the work, and produces tested, production-ready code end to end. A Repo Wiki keeps long-lived context across sessions.

Crowdsourced LLM leaderboard where humans vote on anonymous model battles.

An open evaluation platform where a user enters a prompt, two anonymous models answer side by side, and the user picks the better response. Those millions of blind pairwise votes are aggregated into Elo-style rankings across text, vision, coding, and other arenas. It works directly with major AI labs and has become the most-cited public reference for comparing frontier model quality.

Ambient AI medical scribe that documents clinical visits.

DeepScribe is an ambient AI platform that listens to natural patient-clinician conversations and automatically drafts clinical notes, cutting time spent on documentation. Beyond the scribe, it automates medical coding (E/M, ICD-10, HCC), offers pre-visit intelligence, and lets clinicians customize how notes are generated. It is aimed at practices and specialty care, with EHR integration.

AI learning companion atop a community homework-help platform.

Brainly is a global learning platform where students get homework help backed by a moderated base of community and expert answers. It layers AI on top of that knowledge base — an assistant named Ginny that simplifies, expands, and personalizes answers across school subjects and grades. The free Q&A community is supplemented by a paid Brainly Plus tier.

Conversational AI inside-sales agent for real-estate leads.

Structurely runs an AI inside-sales agent that engages new real-estate and mortgage leads over SMS, web chat, and voice, qualifying them on timeline, budget, and motivation. It books appointments, performs live phone transfers to a human agent, and keeps nurturing leads for over a year until they are sales-ready. It plugs into CRMs such as Follow Up Boss, HubSpot, and Salesforce.

Bot-free AI notetaker that records and summarizes meetings.

Bluedot captures, transcribes, and summarizes online and in-person meetings without sending a bot into the call — recording happens through the browser extension or desktop app instead. It generates use-case-tailored notes and can push summaries to your CRM, Notion, and other tools. Works across Google Meet, Zoom, Microsoft Teams, Webex, and live conversations.

AI podcast player with chapters, episode summaries, and shareable highlights.

Snipd is an AI-powered podcast app that transcribes episodes, breaks them into chapters, and generates summaries and key takeaways you can read before listening. While playing, it detects highlight-worthy moments and lets you save them as 'snips' — short clips with auto-generated transcripts and notes — and you can chat with an episode's content. Built by a Zurich-based team, it positions podcast listening as active learning.

Enterprise platform for AI security, governance, and trust.

Cranium helps enterprises see, secure, and govern the AI across their organization by discovering models, datasets, and pipelines and assembling them into an AI Bill of Materials (AI-BOM). It runs automated evaluations and red-teaming to surface unsafe behavior, configuration gaps, and compliance risk, and monitors AI systems in production. The platform targets security, risk, and compliance teams standing up responsible-AI programs.

AI that turns research papers into structured, referenced summary flashcards.

Scholarcy reads full-length academic papers, articles, and book chapters and breaks them into interactive summary flashcards that surface the synopsis, key findings, methods, figures, tables, and references. It imports from PDFs, Google Drive, Zotero, and the web, and highlights cited claims so researchers can grasp a paper's core arguments quickly. A premium Scholarcy Library adds unlimited use plus saving, annotating, sharing, and exporting of flashcards.

Ethical AI voice cloning and speech-to-speech for film, games, and media.

Respeecher is a synthetic-voice platform built for professional media production, offering voice cloning, speech-to-speech conversion, and text-to-speech. Its speech-to-speech model maps one performer's delivery onto a target voice while preserving the original emotion and timing, and in-house sound professionals refine the output. The company is known for high-profile film, TV, and game work, from Star Wars to Cyberpunk 2077.

AI-powered translation management for software, websites, and apps.

Transifex is a SaaS translation management system (TMS) that combines automated localization workflows, AI translation, and team collaboration. Transifex AI leverages your glossaries, style guides, and translation memory to keep tone and terminology on-brand, while the Translation Quality Index (TQI) scores each string in real time and routes low-confidence content to reviewers. Over-the-air updates push translations live to web and mobile apps without redeploying code.

Open-source AI localization for web and mobile apps, built for developers and CI/CD.

Lingo.dev is a localization engineering platform that translates app content through configurable localization engines persisting glossaries, brand voice, and per-locale model chains. Developers call it from an open-source CLI, a React compiler, a GitHub Action, or the API, so translations regenerate automatically on every commit instead of being pasted into a separate web tool. Customers include Mistral AI, Cal.com, and Solana.

Agentic AI workspace on an infinite canvas with autonomous multi-task agents.

Flowith is an AI workspace built around an infinite two-dimensional canvas, where you branch threads and organize work visually instead of in a linear chat. Its autonomous agent, NEO, plans and executes multi-step tasks with tool calling and persistent context, while the Oracle scheduler breaks complex jobs into subtasks. It supports leading models including GPT and Claude. A free Starter tier offers limited credits, with paid Professional, Ultimate, and Infinite plans.

Open-source AI answer engine that searches the web and cites its sources.

Scira (formerly MiniPerplx) is an open-source, AI-powered answer engine — a Perplexity alternative built on the Vercel AI SDK. It plans a query, retrieves from the web, and returns concise answers with inline citations, drawing on 60+ models including Grok, Claude, Gemini, GPT, and DeepSeek. The AGPL-3.0 code is self-hostable, and a hosted app at scira.ai offers a free tier plus a Pro plan with connectors, memory, and voice.

Turns long videos into short, captioned clips for social in one click.

Vizard is an AI video tool that automatically slices long-form videos — podcasts, webinars, interviews, livestreams — into short, social-ready vertical clips. It transcribes the source, finds the highlight moments, adds auto-captions, and reframes to keep the speaker centered for TikTok, Reels, and YouTube Shorts. A free plan lets you try clipping without signing up, with paid Creator and Business tiers for more exports and longer videos.

Agentic cloud IDE for building and shipping full-stack AI apps with Gemini.

Firebase Studio is Google's cloud-based, agentic development environment for building and shipping full-stack AI apps from the browser. It unifies the former Project IDX with Gemini-powered agents and the Genkit framework, giving you a full Code OSS editor, app prototyping from natural-language prompts, emulators, and one-click deploy to Firebase App Hosting. It runs entirely in the browser with no local setup. The core environment is free, with optional paid Cloud Billing for hosting and higher quotas.

AI enterprise search on a verified company knowledge layer.

Guru is an enterprise knowledge platform combining AI search, a verified company wiki, and an intranet, surfacing trusted answers inside the tools teams already use. Knowledge Agents give departments like HR, sales, and support cited responses grounded in governed content, backed by 100+ integrations and a browser extension.

Agentic AI platform for IT, HR, and customer service desks.

Aisera is an enterprise agentic AI platform that automates service interactions across IT, HR, finance, and customer support. It resolves and deflects tickets autonomously using domain-specific 'Hyperflows' and prebuilt templates, with tools like Agent Composer and LLM Studio to configure conversational and back-office automation in one loop.