AI Apps Directory

Open SDK for production AI agents in .NET and Python.

Microsoft's multi-language framework for building, orchestrating, and operating AI agents and multi-agent workflows. It offers a consistent API across C#/.NET and Python with first-class support for both, plus built-in durability, restartability, observability, and human-in-the-loop control. Provider-flexible, so the underlying models can change without rewrites.

Visual low-code builder for AI agents and RAG apps.

Open-source tool for prototyping and deploying agentic and RAG applications through a drag-and-drop canvas, with Python customization underneath each node. It connects major LLMs, vector databases, and tools, and can expose flows as APIs or MCP servers. Run it locally, as a desktop app, or on managed cloud.

Open-source Python framework for production RAG and agents.

Orchestration framework for building LLM applications as modular pipelines — retrieval, routing, memory, and generation wired together with explicit, traceable data flow. It is model- and store-agnostic, integrating major providers and vector databases behind a stable component API. Aimed at production: serialization, logging, and deployment across cloud or on-prem.

Open-source autonomous coding agent inside VS Code.

VS Code extension that turns the editor into an agentic coder with real file-system access, terminal control, and multi-step task execution. It ships role-specific modes — Architect, Code, Ask, Debug, Test — each with its own prompt and tool permissions, and can hand off between them mid-task. Model-agnostic: connect any provider key, from frontier APIs to a local model, and pay only for your own token usage.

AI melody and chord generator that outputs editable MIDI.

Generative music tool that produces melodies and chord progressions for producers, exporting both MIDI and audio loops you drag straight into a DAW. Its Seeds models are royalty-free, while Collab Club offers signature models co-built with award-winning producers. Runs standalone and via a plugin bridge so generated ideas land directly in your session.

AI-powered operating system for real estate agents and teams.

Lofty (formerly Chime) is an AI-powered platform for real estate professionals that unifies lead generation, CRM, IDX websites, a power dialer, and automation. Its agentic AI features — an AI Assistant, an AI Sales Agent (virtual ISA), Social Agent, and Homeowner Agent — engage leads, schedule appointments, and run follow-ups autonomously. It supports 70,000+ agents and is used by brokerages including Coldwell Banker, Berkshire Hathaway, eXp Realty, and Keller Williams.

Nationwide property data with AI-native and MCP delivery.

ATTOM is a property data provider covering 160M+ U.S. properties, combining public records — deeds, mortgages, assessor, and tax data — with foreclosure, boundary, and neighborhood datasets. It delivers data through a Property Data API, bulk licensing, Snowflake/Databricks connectors, and AI-native cloud delivery including an MCP server, so AI agents and analytics tools can query property data directly.

AI-powered property valuation and real estate analytics.

HouseCanary is a property valuation and analytics platform covering 136M+ U.S. properties. It uses machine learning — including image recognition that reads home condition from photos — to produce automated valuations (AVMs), comparables, market forecasts, and portfolio monitoring, plus CanaryAI, a generative AI assistant. It serves mortgage lenders, single-family-rental investors, REITs, and agents through an API and web products.

Generative AI for property development, zoning, and plan review.

Archistar is an AI platform for property development and the built environment. It combines generative design, computer vision, and machine learning to analyze sites against planning and zoning rules, assess development feasibility, and automate building-code and zoning compliance checks (its AI PreCheck plan-review tool) for permit applications. It serves property developers, architects, and local governments to speed approvals and de-risk projects.

Computer vision and AI for real estate property imagery.

Restb.ai applies computer vision and AI to real estate photos at scale — classifying rooms, identifying interior and exterior features, scoring property condition and quality, recognizing architectural style, and generating image captions. Its API processes millions of listing images daily for AVMs, iBuyers, MLSs, portals, appraisers, and insurers, turning unstructured photos into structured, queryable property data.

Browser-based AI video editor with subtitles, dubbing, and avatars.

An all-in-one online video creation platform: a real timeline editor paired with AI tools for auto-subtitles, translation and dubbing, text-to-speech, AI avatars, background and noise removal, eye-contact correction, and text-to-video generation. Runs entirely in the browser, aimed at marketers, creators, and teams making social and brand video.

A full-stack voice runtime for building human-sounding AI agents.

A developer platform for real-time voice AI — an integrated STT + LLM + TTS pipeline exposed through REST and WebSocket APIs (OpenAI Realtime-compatible) for companions, character chat, support, and phone agents. Beyond the voice stack it offers a model Router, inference, and compute, with cloud and enterprise on-prem deployment.

Turn your text into editable diagrams, infographics, and visuals.

A visual AI for business storytelling that converts written text — prose, outlines, notes — into editable diagrams, flowcharts, mind maps, and infographics in seconds. Generates multiple visual options from a passage, then lets you tweak icons, connectors, colors, and fonts and export to PNG, PDF, or SVG for decks, blogs, and docs.

Pro-grade AI upscaling, denoise, and detail recovery for photo and video.

A suite of AI image- and video-enhancement apps — Topaz Photo, Topaz Video, and Gigapixel — that upscale (up to 16x), denoise, sharpen, deblur, and recover detail using proprietary models that render locally on your GPU. Long the default for photographers, restorers, and post houses, with newer cloud and API options alongside the desktop apps.

Real-time speech-to-text and audio intelligence through a single API.

End-to-end audio infrastructure to record, transcribe, and enrich speech via one API — real-time streaming under ~300ms latency, batch transcription, diarization, translation, and summarization across 100+ languages. Reengineered Whisper for production before shipping its own Solaria models, with EU data residency for compliance-bound teams.

Prompt CMS, evals, and observability for LLM teams.

PromptLayer is a prompt-engineering platform that treats prompts as a content-managed asset: version, edit, and deploy them without touching application code. It pairs that registry with an evaluation harness (datasets, scoring) and an observability stack that logs every request and tracks cost and latency. The collaborative model lets non-technical domain experts iterate on prompts alongside engineers.

Private, on-device audio and video transcription for Mac.

MacWhisper transcribes audio and video files entirely on your Mac — no internet connection and no data leaving the machine. Drop in MP3, WAV, MOV, or MP4 and get a transcript with speaker labels, timestamps, and 50+ export formats. It runs OpenAI's open-source Whisper (and Nvidia's Parakeet) locally, hitting roughly 30x realtime on Apple Silicon via Metal acceleration.

No-code platform to build, launch, and scale AI agents.

Voiceflow is a no-code platform for designing, testing, and shipping chat and voice AI agents for customer support, lead generation, and beyond. A visual canvas lets designers, PMs, and developers collaborate on conversation logic, connect a knowledge base for RAG, and deploy to web widgets, phone, or any channel via API. It supports multiple model providers and scales to enterprise call and message volumes.

Open-source platform for the ML and GenAI lifecycle.

MLflow is an open-source platform for managing the full machine-learning and GenAI lifecycle — experiment tracking, model registry, deployment, and, more recently, LLM/agent observability. Its GenAI stack adds OpenTelemetry-based tracing, systematic evaluation with built-in metrics and LLM judges, and prompt versioning. Framework- and provider-agnostic, it runs on your own infrastructure with no vendor lock-in.

A private, AI-organized place to remember everything.

mymind is a personal memory tool: save notes, links, articles, images, and quotes, and it auto-tags and sorts them for you — no folders, no manual filing. AI recognizes what each item is (article, product, recipe, book) and surfaces it again through fast visual, associative search. It's built privacy-first, with no ads, no tracking, and nothing sold or used to train models.

Open-source, local-first workspace for docs, whiteboards, and databases.

AFFiNE is a local-first workspace that combines block-based docs, an infinite whiteboard canvas, and databases — an open-source alternative to Notion and Miro. Pages flip between document and edgeless (canvas) modes, and AFFiNE AI helps draft, summarize, and turn outlines into mind maps and slides. It runs on web, desktop, and mobile, with self-hosting available via Docker.

GPU cloud marketplace for renting AI compute.

Vast.ai is a marketplace for renting GPUs, connecting people who need AI compute with hosts who list spare hardware — from solo owners to Tier-4 data centers. Prices are set by supply and demand, billed per second, and queryable through code. It supports on-demand, interruptible (spot), and reserved instances across tens of thousands of GPUs and dozens of GPU types.

Build native mobile apps by chatting with AI.

Rork turns plain-language prompts into working iOS and Android apps. Its Pro tier generates React Native + Expo projects you can preview live and ship to the App Store and Google Play, while Rork Max builds native SwiftUI apps compiled with Xcode. It focuses on mobile as the target surface rather than web pages, and produces real native apps instead of web wrappers.

Persistent memory layer for AI coding agents.

ByteRover gives coding agents long-term, structured memory that persists across sessions and tools. It organizes project knowledge into hierarchical context trees, stores them locally by default, and serves relevant context back to agents through an MCP server and CLI. It plugs into Cursor, Claude Code, Windsurf, and other assistants, and an optional cloud tier lets teams sync and share context.