AI Apps Directory

Data labeling and quality platform for training and evaluating AI models.

Kili Technology is a data-centric platform for turning raw data into high-quality training and evaluation datasets. It supports annotation across image, video, text, OCR, and geospatial data, with review and quality workflows, plus LLM evaluation and RLHF using human-in-the-loop and LLM-as-a-judge. It is used by enterprises including Airbus and SAP, and offers cloud, private-cloud, and on-premise deployment.

Registry and governance layer for AI agent skills.

Tessl is an agent-enablement platform that lets teams build, share, version, and govern the reusable skills their AI coding agents rely on. It pairs a searchable registry of 3,000+ public skills (plus private workspaces) with a framework to author and test skills, security scanning and policy enforcement, and usage analytics. It integrates with agents including Claude Code, Cursor, GitHub Copilot, and Gemini.

Evaluation, observability, and optimization platform for AI agents and LLM apps.

Future AGI is an end-to-end platform for testing, evaluating, observing, and improving generative-AI applications. It spans simulations, evaluation suites, real-time tracing and dashboards, runtime guardrails, and a model gateway, with multimodal evaluation across text, image, and audio. The core stack is open-source under Apache 2.0 and can be self-hosted or used as a managed cloud.

AI agents that investigate fraud, disputes, and AML cases end-to-end.

Roe AI is an agentic investigation platform for financial-crime teams. Its agents read structured and unstructured data from existing systems, follow a team's standard operating procedures, and produce cited, examiner-ready dispositions for fraud, chargeback dispute, and AML cases. It is used by card issuers, BNPL providers, marketplaces, and crypto compliance teams.

Generate editable iOS and Android app designs from a prompt.

Sleek is an AI mobile app designer that turns text prompts or reference images into iOS and Android UI. Designs are editable on a visual canvas and export to Figma or to React/HTML with Tailwind CSS. It also exposes an API and agent skills so AI coding tools can generate app screens directly. It targets non-technical founders, product managers, and developers prototyping mobile apps.

Enterprise AI video dubbing and translation with lip sync.

Dubly.AI is a video localization platform for translating and dubbing content with voice cloning and lip synchronization. It supports glossaries, optional native-speaker review, 4K export, large file uploads, and team workspaces, and runs on GDPR-compliant infrastructure hosted in Germany. It covers 32+ languages and is aimed at enterprise content and publishing teams.

AI video translation with dubbing, lip sync, and voice cloning.

Vozo is an AI video platform that translates and dubs videos into other languages while preserving the original speaker's voice. It combines automatic transcription, translation, voice cloning, lip-sync, subtitle generation, and on-screen text translation in a single editor, plus an API for higher-volume workflows. It supports 160+ languages and targets creators, marketers, and localization teams.

Security toolkit that sanitizes and screens LLM prompts and responses.

LLM Guard is a security toolkit for large language model applications. It runs prompts and model responses through configurable scanners — prompt-injection and jailbreak detection, PII redaction, toxicity and bias checks, and secrets scanning — to sanitize input and validate output before it reaches users. It ships as a Python library you wrap around your own LLM calls, with the scanners running locally.

Agentic AI platform for turning proprietary data into decision-grade artifacts.

Capitol is an agentic AI platform that turns proprietary data and expert judgment into trusted, decision-grade artifacts — due-diligence reports, regulatory documentation, and executive briefings. Built for regulated, high-stakes institutions in financial services, professional services, and government, it runs entirely inside enterprise infrastructure with no data egress and keeps every output auditable. It is model-agnostic, working with whichever LLMs an organization approves, and exposes a web interface plus an API and SDK for builders.

Ambient AI medical scribe for clinical documentation.

Sunoh.ai is an ambient AI medical scribe that listens to natural patient-provider conversations and turns them into structured clinical documentation. Beyond the note, it generates a visit summary and pre-fills orders for medications, labs, imaging, and referrals, which clinicians review before signing. It is EHR-agnostic, working across Epic, Athenahealth, and Cerner, and runs on iOS, Android, iPad, and the web. Pricing is a flat $149 per user per month.

Computer-vision defect detection for manufacturing, trained from CAD.

Bucket Robotics builds computer-vision defect detection for manufacturing that trains from CAD files and synthetic data instead of hand-labeled photos. It generates simulated defects — burn marks, bumps, breaks — from the CAD that every modern part already has, producing production-ready vision models that deploy in minutes and adapt as parts and lines change. The system integrates into existing production lines without adding new hardware, and has drawn early customers in automotive and defense.

Gamified AI study app that turns your notes into flashcards and quizzes.

Gizmo is a mobile-first study app that turns notes, PDFs, slides, and YouTube videos into adaptive flashcards and quizzes built around spaced repetition and active recall. It wraps studying in game-like mechanics — daily lives, streaks, and bite-sized quizzes — to make revision feel closer to a social app than a textbook. Used by more than 13 million learners across 120 countries, it targets exam prep from GCSEs and A-levels to AP and college courses. A free tier covers daily quizzes and limited tutoring, with paid plans unlocking unlimited use.

AI reliability platform for monitoring and fixing AI and IT systems.

InsightFinder is an AI-driven reliability platform that detects anomalies, pinpoints root causes, and remediates issues across both AI systems and traditional IT infrastructure. It ingests metrics, logs, traces, and events, applying 'composite AI' — streaming anomaly detection plus deterministic causal analysis — and ships fine-tuned, domain-specific small language models rather than relying on generative AI alone. Its ARI agent runs end-to-end incident management: detection, diagnosis, evidence collection, and real-time remediation. The platform runs as SaaS or in fully air-gapped environments and integrates with OpenTelemetry, Datadog, and Prometheus.

AI-native business intelligence and data visualization platform.

Golden Analytics is a web-based business intelligence platform that combines data connection, discovery, preparation, analysis, and dashboarding in one tool. It profiles datasets automatically, surfaces patterns, and a 'Slider of Autonomy' lets users dial how much the AI does versus how much they drive themselves — taking a raw dataset to a shared dashboard in as little as two clicks. It offers a free tier, with Team and Enterprise plans that include all features without token metering.

Agentic AI data platform for research and analytics.

Zerve is a data platform that brings AI agents, notebooks, automatic data discovery, conversational reports, and deployment into a single canvas for data scientists and analysts. Agentic notebooks assist with exploration and analysis, the platform maps schemas and surfaces patterns from connected data, and finished work can ship directly as an API, app, or dashboard. It offers a free tier, with self-hosted and air-gapped deployments for enterprise.

Frontend stack for building in-app AI copilots and agents.

CopilotKit is a framework for embedding AI copilots and agents directly inside web apps — chat, generative UI that renders live React components, shared application state, and frontend tool calls. It connects to agent frameworks like LangGraph, CrewAI, LlamaIndex, and Pydantic AI rather than shipping its own agent, and offers both headless APIs and prebuilt UI components. The company says its stack is used across the majority of Fortune 500 companies and powers millions of agent-user interactions per week.

Production-grade extraction for complex documents.

A document-extraction platform that converts messy, real-world documents — financial statements, medical records, contracts, spreadsheets — into clean, LLM-ready structured data. Pulse runs its own OCR, layout, and vision models (including its Ultra extraction model) rather than wrapping a general-purpose LLM, and exposes the pipeline through an API that drops into existing data workflows. It offers a free sandbox to try, with enterprise tiers for scale; the company says it has processed over a billion document pages.

Turn unstructured documents into structured data.

An agentic document-processing platform that extracts clean, structured JSON from PDFs, scans, and other complex documents using LLMs. Its Prompt Studio gives a no-code IDE to author and test extraction prompts per field, which you then deploy as APIs or ETL pipelines into your warehouse. Built by Zipstack, Unstract is open source under AGPL-3.0 and self-hostable via Docker Compose, with a managed cloud that adds SSO, human-in-the-loop review, and compliance certifications (SOC 2, HIPAA, ISO 27001, GDPR).

Zero-dependency, token-efficient database MCP server.

An open-source Model Context Protocol server that lets AI coding assistants connect to and query databases through one unified gateway. DBHub deliberately exposes only two tools — execute_sql (with transaction support and safety controls) and search_objects (schema/table/column exploration) — to keep the agent's context window lean. It supports Postgres, MySQL, SQL Server, MariaDB, and SQLite, works with clients like Claude Desktop, Claude Code, Cursor, VS Code, and Copilot CLI, and includes a built-in web interface for running queries and viewing request traces.

The continuous-improvement stack for AI agents.

An evaluation and monitoring platform for AI agents, built around the open-source judgeval framework. Judgment traces an agent's full trajectory — tool calls, memory, search queries, and long reasoning chains — then uses trajectory-level judges to surface failure modes, validate fixes before deploy, and catch behavioral regressions in production. The captured environment data and evals feed back into agent post-training (RL and SFT), not just pass/fail scoring. judgeval is Apache-2.0 and free; the hosted platform adds the dashboard, AutoRubrics, and enterprise features.

A desktop AI assistant that sees your screen and works across every app.

Highlight AI is a desktop assistant that reads on-screen context across the apps you use, so you can ask about and act on whatever you're looking at without copying it into a chat box. It captures screen content, voice, and documents to answer questions, summarize, and transcribe meetings locally. A free tier offers unlimited chat with auto-selected base models; Pro unlocks premium frontier models and cloud transcription.

AI-generated functional music engineered to help you focus, relax, and sleep.

Brain.fm streams functional music designed with auditory neuroscience to shift the brain into states for focus, relaxation, meditation, or sleep. Rather than curating existing tracks, it generates music combined with a patented modulation technique intended to drive neural phase-locking. The catalog is organized by goal, with a dedicated mode tuned for ADHD attention.

A set of small AI tools to help neurodivergent people get unstuck.

Goblin Tools is a collection of single-purpose AI utilities aimed at people who find everyday tasks overwhelming. Its best-known tool, Magic ToDo, recursively breaks a vague task into smaller steps with an adjustable difficulty ('spiciness') setting. Others reword text for tone (Formalizer), gauge the mood of a message (Judge), explain things simply (Professor), estimate effort, and turn brain-dumps into action lists.

AI video localization and dubbing with voice cloning.

Rask AI is a video localization and dubbing platform that translates and re-voices video and audio into 130+ languages. It generates synthetic voiceovers with voice cloning in 32 languages, adds automatic lip-sync, detects multiple speakers, and produces translated captions and subtitles. Aimed at creators and marketing teams adapting content for global audiences, it runs in the browser and via API.