AI Apps Directory

Security posture and threat detection for SaaS and AI agents.

Reco is a SaaS security platform that discovers and secures the apps, identities, and AI agents running across an organization. It maps human and non-human identities, surfaces shadow AI and misconfigurations, and detects threats across 200+ integrated applications. Its AI Agent Security adds visibility and control over autonomous agents like Copilot and Agentforce.

AI agents that investigate financial fraud for institutions.

Finic builds AI agents that automate fraud investigations for banks and fintechs. Its agents connect to existing tools through the browser like a human analyst, pull structured and unstructured data, triage cases, and write up case notes — letting fraud-ops teams clear far more reviews without added headcount. Founded by engineers from Robinhood's identity team.

Open-source text- and image-to-video generation from Alibaba.

Wan is an open-source family of video generation models from Alibaba's Tongyi Lab, covering text-to-video, image-to-video, and image generation and editing. Released under Apache 2.0 with weights, training, and inference code public, it can be self-hosted or used free on the wan.video site. Successive versions, including Wan 2.2's mixture-of-experts architecture, have topped open-video benchmarks.

Transcribe, subtitle, dub, and voiceover in 125+ languages.

Maestra is a cloud media platform that converts audio and video to text, then generates translated subtitles, AI voiceovers, and dubbing across 125+ languages. It handles transcription, captioning, translation, and live captions in one workspace, with an editor for cleanup and export. Built by Katara Tech for creators and enterprise localization teams.

AI coding agent for your IDE and terminal.

Zencoder is an AI coding agent that indexes an entire repository to understand its architecture and dependencies, then writes, tests, and fixes code across the development lifecycle. Its Zen Agents are customizable, shareable autonomous agents for tasks like generating tests, updating dependencies, or opening PRs, while Zentester focuses on automated unit and end-to-end tests. It runs inside popular IDEs like VS Code and JetBrains and via a CLI, supporting 70+ languages.

Speech-to-speech platform for reliable voice agents.

Phonic is a platform for building production voice agents on its own end-to-end speech-to-speech models, rather than chaining separate speech-to-text, LLM, and text-to-speech stages. It targets sub-300ms latency for natural turn-taking and reliable tool calling, and bundles evaluation, session records, and real-time observability to surface failure points. Aimed at enterprises, it offers cloud API access plus containerized deployment in your own environment.

Rerankers and embeddings that sharpen AI retrieval.

ZeroEntropy builds specialized models — rerankers, embeddings, and custom retrieval models — that improve search accuracy in RAG pipelines and agentic apps. Its zerank rerankers reorder retrieved results so the most relevant passages reach the model, reportedly beating Cohere and Gemini rerankers at lower cost. The models are served through a single, latency-optimized API with Python and TypeScript SDKs, and the smaller zerank model is released as open weights.

Sandbox-native cloud for AI agents.

Tensorlake is a cloud platform that gives AI agents their own isolated, stateful sandboxes for running code and calling tools safely. Each sandbox is a microVM that can pause and resume, so long-running agentic loops keep their state across restarts and can run for hours. It exposes serverless Python workflow APIs that scale to zero when idle, and its earlier document-parsing and OCR API now runs as one workload on top. A free tier is available.

Explore, structure, and analyze millions of unstructured records as interactive embedding maps.

Nomic Atlas is a data-intelligence platform that embeds large collections of text, image, and audio data and renders them as interactive 2-D maps you can browse, search, cluster, and label in the browser. Powered by Nomic's own embedding and topic-modeling models, it scales from hundreds to tens of millions of points and exposes the same pipeline through a developer API for embeddings and retrieval.

High-accuracy document parsing — PDFs and images to markdown, JSON, and HTML.

Datalab turns PDFs, images, and office documents into clean markdown, JSON, and HTML with layout, table, math, and code preservation. It is the commercial, hosted layer over the open-source Marker converter and Surya OCR toolkit, offered as a pay-as-you-go API with a free monthly allowance, while the underlying models stay free to self-host for research and small startups.

AI-powered studio for recording, editing, and producing audio and video.

Podcastle is a browser-based content-creation platform for podcasters and video creators: multi-track remote recording, AI text-to-speech and voice cloning, transcription, and one-click audio and video editing with noise removal and leveling. It bundles studio capture, AI voices, and editing into a single workflow so creators don't need a separate DAW or video editor.

Best-in-class embedding and reranking models for retrieval and RAG.

Voyage AI builds retrieval-specialized embedding and reranking models served via API to ground LLM applications. Its voyage-3 series of text and code embeddings, domain-tuned variants, and rerank models (e.g. rerank-2.5) are aimed at higher RAG accuracy than general-purpose embeddings. Now part of MongoDB, its models are being woven into Atlas Vector Search while the standalone API continues to operate.

Multi-model AI art generator wrapped in a creative community.

NightCafe is a browser-based AI art platform that generates and edits images from text prompts across many engines in one place — FLUX, Stable Diffusion, DALL·E, Google Imagen, Ideogram and more — plus image-to-video and style-transfer tools. It runs on daily free credits and a credit-pack/PRO model, and is built around an active community with shared galleries, chat rooms, and a daily AI Art Challenge.

An AI tutor that turns your study materials into lessons.

YouLearn ingests PDFs, YouTube videos, slides, lecture recordings, and notes, then turns them into summaries, flashcards, quizzes, transcripts, and audio podcasts — plus a tutor you can chat with that answers grounded in your own material. It runs on the web and as native iOS and Android apps, with a free tier (capped daily chats and uploads) and paid Pro and Max plans.

AI SEO writer that turns a keyword into a ranking article.

Koala AI is a content suite built around KoalaWriter, which generates publish-ready long-form articles using real-time SERP analysis to fold in the keywords, topics, and entities top results rank for. It pairs with KoalaChat, KoalaImages, internal-linking, and lead-magnet tools, and publishes directly to WordPress, Shopify, Webflow, and Ghost. A limited free trial precedes paid plans starting at $9/month.

Open-source AI agents that pentest your app and prove findings.

Strix runs autonomous AI agents that behave like real attackers: they execute your code dynamically, explore the app through an HTTP proxy and headless browser, and surface vulnerabilities — then validate each with a working proof-of-concept instead of a static-analysis guess. It runs locally via Docker from the CLI, against a local codebase, a GitHub repo, or a black-box web target, with a hosted cloud version and GitHub Actions integration for CI.

AI-powered UI design for non-designers.

Visily turns text prompts, screenshots, and hand-drawn sketches into editable wireframes, mockups, and clickable prototypes on a single collaborative canvas. It targets non-designers — founders, PMs, and engineers — with drag-and-drop components, AI-assisted layout, and a short learning curve. Designs import from and export to Figma, and a generous free Starter tier needs no credit card.

AI-powered text adventure that turns your every action into an open-ended story.

AI Dungeon is an AI-driven text adventure where the model acts as a dungeon master, generating an open-ended story that responds to whatever you type — any action, any genre, with no fixed script. Players can pick from preset settings or author custom scenarios and worlds, and the game keeps track of characters and events as the narrative unfolds across web and mobile.

AI legal intelligence that detects large-scale violations and sizes litigation before it's filed.

Darrow is an AI legal-intelligence platform that scans public data to surface harmful events — data-privacy breaches, antitrust, environmental, and financial violations — then estimates the number of victims, predicts outcomes, and sizes a case's value. Its 2026 platform lets plaintiffs' firms run case discovery, evaluation, and portfolio management in one workflow, positioning itself 'upstream' of litigation rather than on downstream legal operations.

Local, open-source AI app builder that runs on your machine with your own API keys.

Dyad is a desktop AI app builder — like Lovable, v0, or Bolt, but running locally on your own machine. You describe an app and it scaffolds full-stack web projects, bringing your own keys across providers (OpenAI, Anthropic, Google, Ollama, LM Studio), with built-in Supabase, GitHub, and Vercel integration plus security scanning. The core is open source under Apache 2.0.

No-code legal document automation plus AI contract drafting and review for lawyers.

Gavel pairs Gavel Workflows — a no-code platform that turns intake answers into finished Word documents and PDFs — with Gavel Exec, an AI contract reviewer and drafter that runs both as a Microsoft Word add-in and on the web. Exec applies a firm's own playbooks and precedent to generate first-pass reviews, redlines, and clauses, benchmark language against market standards, and run batch analysis across portfolios of contracts.

Free AI-powered primary care, with every diagnosis and prescription reviewed by real physicians.

Lotus Health is a consumer primary-care app whose AI conducts patient consultations and drafts diagnoses, prescriptions, lab orders, and referrals, with board-certified physicians reviewing each before it's finalized. Care is free to patients, licensed across all 50 US states, and available 24/7 in dozens of languages; urgent cases or anything needing a physical exam are routed to in-person care.

Managed RAG-as-a-service — the context engine for AI agents and apps.

Ragie is a fully managed retrieval-augmented-generation platform. It ingests data through native connectors like Google Drive and Notion, parses multimodal content (PDFs, images, audio, video), and serves hybrid vector + keyword + summary retrieval over an API and MCP server. Developers add accurate, grounded context to LLM apps without building their own ingestion and retrieval pipeline.

Open-source agent memory that retains, recalls, and reflects.

Hindsight is an open-source memory system for AI agents that works like human memory — organizing world facts, agent experiences, entity summaries, and evolving beliefs into four networks. Its retain/recall/reflect operations let agents reflect on past runs and update beliefs instead of repeating mistakes. It was built by Vectorize with Virginia Tech and The Washington Post.