AI Apps Directory

AI YouTube summarizer that turns any video into key takeaways and timestamps.

Eightify is an AI summarizer for YouTube, delivered as a browser extension with companion mobile apps. It condenses a video into key insights, a short overview, and timestamped sections so you can grasp the main points in seconds and jump straight to what matters, with summaries and translations in 40+ languages. Summaries are generated using ChatGPT and Claude, and it handles videos up to several hours long.

Agentic legal AI that drafts, reviews, and negotiates contracts from your playbooks.

Genie AI is a legal AI platform for drafting, reviewing, editing, and negotiating business contracts. It can generate personalized, jurisdiction-aware agreements — up to 50+ pages — in minutes, flag risks in existing documents, and learn an organization's standards and playbooks to keep edits on-policy. London-based, it offers a free tier plus paid Pro, Business, and Enterprise plans for in-house legal teams and firms.

AI builds interactive, discussion-driven lessons that teachers run live with their class.

Curipod is an AI lesson-building platform for teachers: enter a topic, grade level, and objective and it generates interactive slide decks with polls, word clouds, open questions, and drawing prompts that students answer live on their own devices. It gives real-time AI feedback on student writing and produces participation reports, aiming to drive classroom dialogue rather than passive viewing. Built for K-12 classrooms, it offers a free tier plus school and district licenses.

Source-linked financial data extracted from filings, feeding analyst models, AI agents, and LLMs.

Daloopa automatically extracts and standardizes fundamental financial data — from SEC filings, investor presentations, and earnings materials — for 5,500+ global tickers with up to 14 years of history, linking every number back to its source document for auditability. Analysts use it to build and update models faster, cutting time spent during earnings season. The same data is exposed to AI tools via API, an Excel add-in, and Model Context Protocol connectors for ChatGPT, Claude, Perplexity, and Rogo.

Ambient AI scribe and clinical decision support that drafts notes and differentials for clinicians.

Glass Health is a clinical AI platform for physicians that pairs an ambient scribe with decision support: it listens to a visit and drafts the note, then generates three-tier differential diagnoses and assessment-and-plan suggestions with PubMed-cited reasoning. Clinicians review, edit, or reject every suggestion — it is positioned as a reasoning aid, not a diagnostic replacement. Higher tiers integrate with EHRs including Epic, athenahealth, eClinicalWorks, and Elation.

Visual, whiteboard-based knowledge base with AI for understanding what you read.

Heptabase is a visual note-taking and research tool that organizes ideas on infinite whiteboards built from linked cards, with a block editor, PDF annotation, web clipping, and bidirectional links. Its AI lets you ask questions and get cited answers across your PDFs, YouTube videos, notes, and journals, and an AI Tutor runs structured, personalized learning sessions. It runs on Mac, Windows, Linux, iOS, Android, and the web with offline support.

AI-powered academic search across 200M+ papers with one-sentence TLDR summaries.

Semantic Scholar is a free scholarly search engine from the Allen Institute for AI that indexes over 200 million papers across every field of science and uses NLP to surface the most relevant and influential work. Its TLDR feature generates ultra-short, one-sentence summaries of papers, and the Semantic Reader adds inline citation cards and skimming highlights to PDFs. An open API and adaptive Research Feeds let developers and researchers build on the same corpus.

AI data analyst that investigates business questions against a governed semantic layer.

Zenlytic is a self-serve business intelligence platform whose AI analyst, Zoë, answers natural-language questions by reasoning over a governed semantic layer rather than raw tables, so results map to agreed business definitions. It connects to warehouses like Snowflake, BigQuery, Redshift, and Databricks plus dbt and Looker semantic models, and returns inspectable analyses, visualizations, and reports inside the app or via Slack and Teams. The emphasis is on auditable, defensible answers for non-technical users.

Wrist-worn personal AI that listens to your day and remembers it for you.

Bee is an ambient personal-AI wearable: a $49.99 wristband (the Bee Pioneer) with dual microphones that continuously records and transcribes the conversations around you, then surfaces summaries, to-dos, reminders, and personal insights in its companion app. It connects to email and calendar so it can draft messages and create events from what it hears. The device works without a mandatory subscription; an optional premium tier unlocks advanced search and specialized agents.

Premium human data and RLHF for frontier AI labs.

Surge AI provides high-quality human-generated training data and reinforcement learning from human feedback (RLHF) for AI developers. It pairs a large network of expert annotators with a labeling platform and API to produce complex, specialized data — code, math, safety, and domain reasoning — used to train and align frontier models. Reported customers include OpenAI, Anthropic, Google, and Meta.

Automated AI red teaming, runtime protection, and governance.

SPLX is an AI security platform that runs automated red teaming against LLM apps and AI agents, simulating thousands of adversarial attacks — prompt injection, jailbreaks, data leakage — to surface vulnerabilities. It adds AI asset discovery, system-prompt hardening, runtime protection, and governance across the AI lifecycle, plus Agentic Radar, an open-source scanner for agentic workflows. It targets security teams shipping AI to production.

Open-source orchestration for data, AI, and infrastructure workflows.

Kestra is an open-source orchestration platform for building data, AI, and infrastructure pipelines as declarative YAML workflows. It is event-driven and language-agnostic, running Python, Bash, Node, Go, or containers across 1,500+ plugins, with a web UI for monitoring plus governance features like RBAC and audit logs. It ships as free self-hosted open source alongside paid Cloud and Enterprise editions.

Computer-vision data curation, labeling, and model pretraining.

Lightly is a computer-vision data platform that helps teams curate the most informative samples from large image and video datasets using embeddings, active learning, and near-duplicate detection. Its suite spans LightlyStudio (curation and labeling), LightlyTrain (self-supervised pretraining and fine-tuning of vision models), and LightlyEdge (smart data selection on devices). The aim is to cut labeling cost by training on the data that actually improves models.

Platform for building multimodal AI datasets and evaluation pipelines.

SuperAnnotate is an enterprise data platform for creating, managing, and evaluating high-quality datasets for AI. It spans annotation across images, video, text, audio, and LiDAR, with AI-assisted labeling, customizable workflows, and an optional managed annotation workforce. Teams use it to build human-in-the-loop data and evaluation pipelines for agentic, multimodal, and frontier AI.

Automated AI transcription in 100+ languages.

Good Tape is an AI transcription tool that turns audio and video into accurate, searchable text across 100+ languages with automatic language detection. It adds speaker identification, AI summaries, and smart search, and is built around a privacy-first posture: GDPR compliance, ISO 27001 certification, EU-based servers, AES-256 encryption, and a commitment not to use uploads to train AI. It runs on the web plus iOS and Android apps.

No-code platform to build and deploy AI agents anywhere.

MindStudio is a no-code platform for designing, building, and deploying AI agents. You assemble agents visually and ship them to web apps, browser extensions, email triggers, scheduled automations, APIs, and MCP servers, with optional custom JavaScript or Python for advanced steps. It connects 1,000+ apps and gives access to 200+ AI models through one interface, charging model usage at provider cost with no markup.

Agentic browser that plans and executes web tasks for you.

Fellou is an AI browser that goes beyond chat by embedding agents that autonomously carry out multi-step web work — deep research across many tabs, competitor analysis, form filling, file handling, and cross-app workflows — from a natural-language prompt. It first generates a step-by-step action plan you can review and edit, then executes it while letting you intervene at any step. It runs as a downloadable desktop browser and can analyze local files dragged into the interface.

Build and share AI mini-apps from a plain-language description.

Opal is an experimental Google Labs tool for building AI mini-apps without code. You describe a task in natural language and Opal generates a workflow that chains prompts, models, and tools, which you can refine in a visual node editor and share with others via a link. It targets marketers, analysts, and other non-engineers who want to prototype and ship small AI-powered tools quickly.

High-performance Python framework for multi-agent systems.

Agno is an open-source Python framework for building multi-agent systems with memory, knowledge, tools, and reasoning. Agents are fast to instantiate and can be composed into teams, and the companion AgentOS runtime serves them in production as a FastAPI app with a control plane.

Program — don't prompt — your language models.

DSPy is an open-source Python framework for building LLM applications by writing modular code instead of brittle prompt strings. You declare input/output signatures and compose modules, then DSPy compiles and optimizes the underlying prompts — and can even tune model weights — for classifiers, RAG pipelines, and agent loops.

AI meeting assistant that records, transcribes, and summarizes.

Fellow is an AI meeting assistant and notetaker that transcribes, summarizes, and extracts action items from calls with human-level accuracy. It offers both bot-based and botless recording, works across Zoom, Google Meet, and Teams, and its Ask Fellow agent answers questions across past meetings.

Build and deploy AI agents as APIs, with MCP tools built in.

Toolhouse is a backend-as-a-service for AI agents: define an agent in plain language or code and deploy it as an API in one command. Agents connect automatically to the Toolhouse MCP server, which provides RAG, memory, code execution, browser use, and 1,000+ tool integrations over the Model Context Protocol.

Real-time AI translation and captions for meetings and events.

Wordly delivers real-time AI translation, live captions, transcripts, and summaries for meetings and events across dozens of languages — no special equipment or human interpreters required. It works with Zoom, Teams, Google Meet, Webex, and in-person events, and attendees join translated audio or captions from a browser or the mobile app.

Eval and observability ops platform for AI product teams.

Freeplay is an LLM evaluation and observability platform that unifies prompt management, batch evals, experiments, and production monitoring in one workflow. Built for cross-functional teams, it lets engineers, PMs, and domain experts review the same traces, run model-graded and code-based evals, and align auto-evaluators with human labels before shipping.