AI Apps Directory

Visual graphs that map the literature around any academic paper.

Connected Papers builds an interactive similarity graph around a seed paper, clustering related work by how strongly papers share references and citations rather than direct links alone. Researchers use it to get up to speed on a field, find prior and derivative work a keyword search misses, and explore a visual map of a research area. The free tier allows a handful of graphs per month, with unlimited graphs on paid academic and business plans.

AI music studio for studio-quality singing vocals from MIDI and lyrics.

ACE Studio generates expressive, human-like singing vocals from MIDI and lyrics, edited in a piano-roll where you control pitch, timing, vibrato, pronunciation, dynamics, and emotional intensity. It ships 140+ royalty-free AI voice models across eight languages, plus AI instruments, voice cloning, stem splitting, and choir/ensemble modes. It runs as a standalone desktop app and as VST/AU/AAX plugins, with vocal generation processed in the cloud.

VMs and Git for AI agents — run, version, and deploy the code AI writes.

Freestyle is cloud infrastructure for AI app builders and coding agents. Freestyle VMs are full Linux micro-VMs that provision in under 600ms with live forking and pause/resume, while Freestyle Git provides API-first Git filesystems with branching and GitHub sync that agents can read from and commit to. Together they give an agent a place to write, run, version, preview, and deploy a full-stack app.

Perpetual secure sandboxes that keep AI agents on warm standby.

Blaxel is serverless infrastructure for AI agents: secure sandboxes that spin up in seconds, hibernate after a second of inactivity at zero idle cost, and resume in roughly 25ms with full memory and filesystem state intact. It co-hosts agents, MCP servers, and batch tasks on one backbone, and adds an LLM gateway with caching, rate-limiting, and observability. Snapshots and forking let teams branch agent state for rapid experimentation.

Cloud Devboxes and benchmarks for running AI coding agents at scale.

Runloop provides isolated, cloud-based development environments — "Devboxes" — where AI coding agents safely execute code with full filesystem, build-tool, and compiler access. Teams spin up thousands of Devboxes on demand for large-scale agent tasks and tear them down when done. A benchmarking suite lets you evaluate and compare agents on standardized tests, and enterprise deployments add compliance and VPC options.

AWS's generative-AI assistant for software development.

Amazon Q Developer is AWS's generative-AI coding assistant that supports developers across the software lifecycle. It offers inline code completions, agentic chat, automated code transformation for language and framework upgrades, security scanning, and AWS-aware troubleshooting. It runs in popular IDEs, the command line, and the AWS console, with deep integration into AWS services.

Salesforce's platform for building and deploying autonomous AI agents.

Agentforce is Salesforce's platform for building, customizing, and deploying autonomous AI agents that act on enterprise data. Prebuilt agents handle service, sales, and other workflows, grounded in Salesforce CRM data and Data Cloud and reasoned over by the Atlas Reasoning Engine with enterprise guardrails. The 2025 Agentforce 360 release expanded it into a platform for orchestrating humans and agents together, with tools like Agent Script for custom agent logic.

Observability and tracing built for AI agents.

AgentOps is a developer platform for monitoring, debugging, and evaluating AI agents. It records every LLM call, tool use, and decision in a replayable session trace, with time-travel debugging, token and cost tracking, and agent benchmarking. Its open-source SDK drops into Python or TypeScript agents in two lines and integrates with frameworks like CrewAI, LangChain, Autogen, and the OpenAI Agents SDK.

AI platform for preclinical drug-discovery research.

BenchSci builds AI software for preclinical pharmaceutical R&D, helping scientists generate hypotheses, identify targets, and design experiments faster. Its platform reads and structures public scientific literature plus a customer's proprietary data into a Biological Evidence Knowledge Graph that scientists query in natural language. Its newer EMET agentic research environment chains domain-specific scientific tools, alongside the established ASCEND disease-biology platform used across major pharma.

AI-powered real estate operating system — CRM, marketing, and deals in one super app.

Rechat is an AI-powered operating system for real estate brokerages and agents that consolidates CRM, marketing design, and transaction management into a single platform. Its modules cover contacts and lead routing (People), marketing across websites, email, social, and print (Studio), and deal and compliance tracking (Deals). Its AI assistant, Lucy, generates marketing content and listing sites, drafts client communications, and reads and interprets transaction forms — pulling from MLS data, brand guidelines, and agent preferences.

AI-native CRM that builds itself from your email, calls, and Slack — no manual data entry.

Day.ai is an AI-native CRM that automatically captures and reasons over customer interactions instead of relying on manual data entry. It listens across Gmail/Outlook, Slack, and video meetings — joining Zoom, Google Meet, and Microsoft Teams calls to record, transcribe, and update records — and layers on AI assistants that prep meetings, manage pipelines, and draft follow-ups. Founders describe it as 'the Cursor of CRM,' aimed at replacing the heavy manual interfaces of legacy systems.

AI go-to-market platform that turns intent signals into automated, personalized outreach.

Unify is an AI-native go-to-market platform that helps sales and growth teams build pipeline by combining 25+ intent signals, B2B contact data, and AI agents that research accounts and write personalized outreach. It orchestrates multichannel sequences across email and LinkedIn with built-in deliverability infrastructure, so reps reach high-intent prospects at the right moment. It's aimed at revenue teams that want prospecting, enrichment, and engagement in one system rather than a stack of point tools.

Multimodal platform that makes images and video searchable and structured.

Coactive AI is an enterprise multimodal application platform that pulls context directly from the pixels and audio in images and video — no manual tagging or metadata required. Teams use it to semantically search, label, govern, and structure large visual libraries at scale, turning unstructured media into queryable data. It is aimed at media, retail, and other enterprises with vast image and video archives.

Open-source evaluation and observability for ML and LLM systems.

Evidently is an open-source Python framework for evaluating, testing, and monitoring AI systems — from tabular ML models to LLM apps, RAG pipelines, and agents. It ships 100+ built-in metrics covering data drift, quality, hallucinations, PII leaks, and jailbreaks, plus LLM-as-judge scoring and monitoring dashboards. Evidently Cloud adds a hosted service with no-code evals, alerting, and team management on top of the open library.

Expressive, emotionally controllable text-to-speech, voice cloning, and voice agents.

Fish Audio is a voice AI platform for real-time text-to-speech with emotion tags, voice cloning from clips as short as 15 seconds, speech-to-text, and end-to-end voice agents. Its flagship S2 model targets natural, expressive, multilingual narration, and the company maintains the open-source Fish Speech (OpenAudio) models on GitHub. A free tier covers personal use, with paid plans and an API for commercial use.

Open-source framework for real-time voice and multimodal AI agents.

Pipecat is a Python framework for building voice and multimodal conversational agents that can listen, speak, and see in real time. It orchestrates streaming speech-to-text, an LLM, and text-to-speech into one low-latency pipeline, wiring together 40+ AI services with no vendor lock-in. Client SDKs cover JavaScript, React, React Native, Swift, Kotlin, C++, and ESP32, and Pipecat Cloud offers managed hosting at scale.

Vision-based agents that automate any UI across desktop, mobile, and web.

AskUI builds and deploys computer-use agents that visually detect and operate on-screen elements across operating systems — desktop, mobile, web, embedded, and automotive HMIs — without relying on selectors or accessibility trees. Its AgentOS runtime and Python SDK let teams automate UI testing and workflows and route between models like Claude, Gemini, and OpenAI. It is aimed at enterprise automation and QA.

AI-native design tool that ships production React + Tailwind code.

Subframe is a code-first design tool where you build interfaces from real, code-backed components on a visual canvas and export clean, production-ready React and Tailwind CSS. Designs map deterministically to code — what you draw is the code you ship — and connect to coding agents like Cursor and Claude Code via MCP. It syncs with Figma and auto-generates a custom design system.

AI that adapts reading materials to any level for teachers.

Diffit lets teachers paste a topic, article URL, or YouTube link and instantly generates leveled reading passages with summaries, vocabulary, and comprehension and discussion questions. Outputs can be set to different reading levels and 100+ languages, then pushed straight to Google Classroom. Free for individual educators, with paid Pro and school/district plans.

Mistral's AI assistant and coding agent (formerly Le Chat).

Vibe is Mistral AI's consumer assistant — renamed from Le Chat in 2026 — for chat, web search with citations, document and image analysis, image generation, and a built-in code interpreter. It now doubles as a coding agent with IDE plugins (VS Code, JetBrains, Zed) and a CLI. Free to use, with Pro, Team, and Enterprise tiers, running on Mistral's own European-built models.

All-in-one AI studio for images, video, and characters.

OpenArt is a consumer AI creation platform for generating and editing images and video, building consistent AI characters, and producing multi-scene visual stories. Rather than one proprietary model, it routes across many engines — Stable Diffusion, FLUX, DALL-E, and thousands of community-trained models — and adds LoRA training, canvas editing, and a model-and-prompt marketplace. It began as one of the largest community hubs for Stable Diffusion.

AI platform that automates healthcare operations and patient access.

Notable is an AI platform purpose-built for healthcare that automates administrative and clinical workflows through AI agents. Its low-code Flow Builder lets teams design automations and its natural-language Sidekick assistant runs them across patient access, scheduling, intake, prior authorizations, revenue cycle, and care-gap closure. Deployed across health systems and plans including CommonSpirit, MUSC, and UC San Diego Health.

AI legal assistant purpose-built for in-house counsel.

GC AI is an AI platform for in-house legal teams that drafts, reviews, and researches in seconds. It includes Easy Prompt (turns plain language into legal requests), Exact Quote (verifiable, sourced citations), a Skill Library of reusable workflows, and a Microsoft Word contract agent. Sold per seat to corporate legal departments rather than law firms.

Culturally fluent AI customer-service agents for global enterprises.

Wonderful is an enterprise platform for AI customer-service agents that handle inquiries across chat, voice, and email — and take action to resolve them. Its distinctive bet is localization: agents are tuned per market for language, cultural norms, and regulation, with local teams sent to manage deployment, aimed squarely at non-English-speaking markets. Used across telecom, finance, healthcare, and manufacturing.