AI Apps Directory

Enterprise-grade LLMs, embeddings, and retrieval built for private deployment.

Cohere builds large language models for the enterprise rather than the consumer. Its Command models cover agentic, multimodal, and multilingual generation; Embed and Rerank power high-quality search and retrieval; Aya is a multilingual research family spanning 70+ languages; and North is a workplace AI platform built on top. Cohere's emphasis is data control — models can run in a private VPC, on-premises, or via a managed Model Vault.

No-code platform for AI voice agents that automate phone calls.

Synthflow is an enterprise voice-AI platform for building and deploying AI agents that handle phone calls — inbound and outbound — without code. A visual flow designer, in-house telephony, real-time monitoring, and 200+ integrations across calendars, CRMs, and telephony let teams stand up agents for customer service, appointment scheduling, and lead qualification. It runs on a pay-as-you-go model: build and test free, then pay per call once live.

Open-weight generative models for image, video, audio, and 3D.

Stability AI is the company behind Stable Diffusion and a family of open and proprietary generative models spanning image (Stable Diffusion, Stable Image), video (Stable Video), audio (Stable Audio), and 3D. Its models can be self-hosted under Stability's licensing, called through the Platform API, or used in the DreamStudio web app, giving builders an open alternative to closed image-generation endpoints.

Security and governance gateway for enterprise AI use.

WitnessAI is a unified security and governance platform for how an organization uses AI. It sits as a gateway over employee and AI-agent interactions, giving security teams three things: observability into all AI activity (including shadow AI), policy enforcement and governance, and protection against prompt injection, data leakage, and other model-layer threats. Each customer runs in an isolated, single-tenant environment encrypted with their own keys.

Open-source framework and cloud for realtime voice, video, and physical AI agents.

LiveKit is the realtime infrastructure layer most voice-AI stacks are built on. Its open-source Agents framework wires together streaming speech-to-text, an LLM, and text-to-speech with reliable turn detection, interruption handling, and telephony, so agents can join a session and converse in near real time. You bring your own STT, LLM, and TTS providers; LiveKit handles the low-latency WebRTC transport. It runs self-hosted under Apache 2.0 or as a managed cloud platform.

Open-source AI coding agent for VS Code, JetBrains, and the CLI.

Kilo Code is an open-source AI coding agent that plans, writes, edits, and runs code inside your editor. It offers specialized modes — Code, Architect, Ask, Debug, and Orchestrator — works across VS Code, JetBrains IDEs, and the CLI, and supports 500+ models with bring-your-own-key and zero markup. A free tier plus paid cloud and team options round it out.

Hand-reviewed directory and news hub for the Model Context Protocol.

PulseMCP is a discovery hub for the Model Context Protocol (MCP) ecosystem — a daily-updated, hand-reviewed directory of thousands of MCP servers and clients, validated by live handshake and scored on reliability. Alongside the directory it publishes tutorials, a use-case showcase, an API for programmatic access, and 'The Agentic Loop' newsletter. It is a free resource for finding and tracking MCP integrations.

Discover, govern, and secure the AI agents across your organization.

Pillar Security is an end-to-end platform for securing enterprise AI — from discovering every AI agent, model, and integration in use to red-teaming them and enforcing runtime guardrails. It maps the AI supply chain across code, SaaS, and endpoints, then layers on governance, data-privacy controls, and compliance mapping. It targets AI-specific risks such as prompt injection, jailbreaks, and data poisoning.

Run a team of parallel AI coding agents on your Mac.

Conductor is a macOS app that runs multiple AI coding agents — Claude Code, Codex, and Cursor — in parallel, each in its own isolated git worktree. You dispatch tasks, watch each agent's progress in real time, then review and merge their changes without them stepping on each other. The app itself is free and runs on your own agent subscriptions; Conductor Cloud extends runs beyond your laptop.

All-in-one open-source embeddings database for semantic search and RAG.

txtai is an open-source embeddings database that unifies dense and sparse vector indexes, graph networks, and a relational database into a single store for semantic search and LLM workflows. Beyond vector search it ships retrieval-augmented generation, pipelines, and agents, and can be built with Python or declarative YAML. It runs locally or self-hosted and exposes API bindings for JavaScript, Java, Rust, and Go.

AI website builder that generates sitemaps, wireframes, and style guides.

Relume helps designers and agencies build marketing websites faster by turning a short brief into AI-generated sitemaps, wireframes, and style guides. Its outputs export to Figma, Webflow, and React, and pair with a library of 1,000+ pre-built responsive components. A free-forever tier covers basics, with paid plans unlocking the full component library and unlimited projects.

Autonomous AI customer experience platform for e-commerce brands.

Siena AI is an autonomous customer experience platform built for e-commerce and retail brands, deploying AI agents that resolve support, shopping, and post-purchase questions across email, chat, and social DMs. It handles tasks like order tracking, returns, address changes, and subscription management in over 100 languages, and is designed to blend automation with brand-aligned, empathetic tone. It integrates with existing helpdesk and commerce stacks rather than replacing them.

Generate original songs with AI and release them to streaming platforms.

Boomy lets anyone create original songs in seconds by picking a style and letting its AI compose and produce the track, with controls to tweak instruments, arrangement, and mix. Finished songs can be saved, downloaded, or distributed straight to Spotify, Apple Music, TikTok, and other services, where creators can earn streaming royalties. A free tier allows unlimited creation, with paid Creator and Pro subscriptions adding downloads, more saves, and commercial use.

Agentic meeting platform where AI agents do the work during the call.

Tana is a meeting workspace with native video calling, real-time transcription, and AI agents that act during the call — generating artifacts like PRs, tickets, and storyboards rather than only summarizing afterward. A persistent context graph remembers people, projects, and decisions across meetings, and AI changes go through a human-approval proposal step. It evolved from Tana's earlier supertag-based note app.

Data factory for AI teams — labeling, evals, and human data for training.

Labelbox is a platform for generating and managing training data for AI models, combining annotation tools (Annotate), data curation (Catalog), and model-assisted labeling and evaluation (Model Foundry). It now spans reinforcement-learning data, custom evals, robotics datasets, and an on-demand network of expert human labelers, metered by a usage-based Labelbox Unit (LBU).

Agentic document parsing that turns complex PDFs into AI-ready markdown.

LlamaParse is LlamaIndex's managed document-parsing service: it extracts text, tables, charts, and images from PDFs and 90+ other formats into clean markdown for RAG pipelines. It offers layout-aware and multimodal parsing modes and 100+ language support, and anchors the LlamaCloud platform alongside Extract, Classify, Split, and Index.

Open-source evaluation and tracing for LLM and agent apps.

TruLens is an open-source Python library for evaluating and tracing LLM, RAG, and agent applications. You wrap your app with feedback functions that score outputs on metrics like groundedness, context relevance, and answer relevance, then trace runs and compare versions on a metrics leaderboard. It integrates OpenTelemetry tracing and runs locally with a built-in dashboard.

Charm's glamorous agentic AI coding agent for your terminal.

A terminal-based AI coding agent from Charm, the team behind Bubble Tea and other CLI tools. It plans and edits files, runs commands, and pulls code context via LSP, all inside a polished TUI. It is model-agnostic: bring your own keys for Anthropic, OpenAI, Google, Groq, OpenRouter, and other providers, and switch models mid-session.

Multi-model AI super-assistant with an agent layer for tasks and apps.

An AI platform whose consumer product, ChatLLM, puts many frontier models — GPT, Claude, Gemini, and others — behind one subscription, alongside image generation and a code/app builder. Its DeepAgent layer runs multi-step agentic tasks like dashboards, automations, and app builds. The company also sells an end-to-end enterprise generative-AI and ML platform.

Alibaba's AI assistant for chat, coding, images, and agentic tasks.

The consumer assistant built on Alibaba's Qwen (Tongyi Qianwen) model family, spanning text chat, coding help, document and image understanding, and image generation. Newer releases add agentic "task" capabilities that complete multi-step workflows and act across Alibaba's ecosystem. Free to use on the web and mobile apps.

Describe an app in plain English and get a working full-stack product.

An AI no-code app builder that turns a conversational prompt into a fully functional web app — database, user auth, permissions, and hosting handled for you. It targets non-developers and founders who want to ship custom internal tools and products without writing code. Now operated by Wix following its 2025 acquisition.

Your AI-powered personal knowledge base.

A personal knowledge base that saves, summarizes, and connects content from anywhere — articles, videos, PDFs — then lets you chat with it using the AI model of your choice. Capture from a Chrome or Firefox extension, the web app, or mobile, with spaced-repetition review to keep what you save.

Fast, accurate voice typing for any app.

A desktop dictation app that turns speech into text across any application, powered by its in-house Avalon model and tuned for low latency. Adds a custom dictionary and formatting so dictated text comes out clean, with a free tier and unlimited paid plans.

Turn your voice into polished text in any app.

A voice-to-text dictation app that transcribes speech into formatted, cleaned-up text system-wide across any application. Per-mode model selection lets you assign different local or cloud models to different tasks, with meeting recording, file transcription, and custom vocabulary on top.