Categories
A collaborative prompt experiment where visitors add instructions and see how an AI model responds.
A turn-taking model that helps conversational AI understand who is speaking and when to respond.
An open-source AI agent that edits KiCad PCB design files and verifies them with ERC and DRC.
An open-source runtime helps developers connect model APIs, tools, and interfaces to build streaming AI applications.
An in-memory temporal graph database helps AI agents store and retrieve memories.
A two-minute memory test compares your score in tokens with GPT, Claude, and Gemini.
An interactive research game where players identify human-written social-media posts among AI-generated ones.
Provides managed desktop application environments with monitoring and recovery controls for computer-use agents.
Helps developers configure, deploy, and meter coding agents through an agent chat and API.
Lets AI agents search and contribute firsthand observations about APIs, products, and services.
Guides AI product managers through designing and exporting runnable evaluations for AI features.
Coordinates AI agents working on verifiable math and science problems and records verified results in a public ledger.
Lets users ask questions about YouTube videos and get answers linked to exact timestamps.
Runs AI agents on scheduled loops locally, with REST and MCP interfaces for developers.
A local AI assistant for Mac that helps people research, draft documents, and work with files.
Provides developers an OpenAI-compatible API for using visual AI models through one endpoint.
Shared memory service that helps teams and AI agents retain project context across tools and sessions.
Turns newsletters, work updates, and agent reports into private AI-hosted audio episodes.
Provides AI agents a dedicated Linux machine to operate signed-in apps through an encrypted bridge and consent gate.
A self-hosted AI team automates routine software work in a GitHub repository for developers.
A benchmark for evaluating local language models on generating SVGs from prompts.
Coordinates independently deployed AI agents through shared records with traceable authorization and provenance.
Tracks community reports of errors, instability, and quality drops across AI tools.
Tracks how AI models answer food classification questions and lets visitors test their own prompts.
A marketplace where users find and customize agentic workflows for different outcomes.
Records and ranks companies’ predictions by accuracy, with outcomes settled by machine.
A platform for reporting, verifying, and documenting real-world AI failures for journalists, researchers, and organizations.
Converts URLs, documents, and images into Markdown for AI workflows and automated pipelines.
Connects AI assistants to Mac apps so users can search information and perform actions from their assistant.
A source-linked archive documenting incidents involving AI coding agents and chatbots.
Deploys and manages AI agents for recruiting, concierge services, and business workflows.
Provides agents and developers with unified access to web search, scraping, and data enrichment APIs.
Analyzes AI agent conversations and creates eval-backed pull requests to fix recurring failures.
A private AI chat app for desktop and mobile that keeps conversations on users’ devices.
Turns a question into a researched, fact-checked episode users can listen to in a browser.
An open-source Rust LLM agent that runs in terminals, editors, and self-hosted servers.
Lets people monitor AI agents through shareable live status boards without installing an SDK or signing up.
Tracks AI model prices and compares value to help users choose cost-effective models and estimate usage costs.
An open protocol and public hub where AI agents sign messages and coordinate through channels, bounties, and polls.
Provides teams with AI agents that learn their processes and work across messaging, email, meetings, and connected tools.
A public ledger benchmarks local language models on an RTX 3090 across text, vision, coding, and other tasks.
Tracks coding agents’ work, tests, and revisions so teams can review and approve changes.
Assesses the technical replaceability of a person's job as a companion to the Large Labor Model.
Provides a registry for LLM fine-tunes and lets developers test and deploy them as serverless API endpoints.
Connects AI agents through addresses and inboxes so they can coordinate tasks for their users.
Generates images, videos, photoshoots, edits, and audio for creators using AI tools under one subscription.
Provides realtime AI video generation through an API for developers and creators.
Transforms uploaded photos into low-poly Niu Lai-inspired images for download.
Stores encrypted context cards for attaching personal details to conversations across multiple AI chat services.
Connects business data and websites to AI tools, checks quantum-safe readiness, and creates ads for businesses.
Provides a single API for accessing AI models with transparent token pricing and prompt caching.
A community-ranked directory for discovering and submitting artificial intelligence tools and platforms.
Provides memoized browser-based web data extraction for AI agents at lower recurring cost.
Shares structured, source-linked memories across AI assistants, coding agents, and workflow tools.
A phone-based AI app that rewards users while claiming to save water by running on consumer hardware.
Provides enterprises with a governed semantic layer that turns AI agent queries into verified SQL across their data.
Optimizes and deploys workload-specific inference stacks for teams using open models.
A self-hosted AI agent that runs tasks through terminal and Telegram with human-controlled permissions.
A web-based tool for generating short videos from text prompts or images, with controls for motion and framing.
Helps teams manage AI usage, budgets, provider keys, and model routing from one dashboard.
A gallery for browsing image-generation benchmark outputs by prompt, model, category, and difficulty.
A CLI for researching text watermarks while ensuring visible text never changes.
Connects company tools to answer questions, track activity, and turn meeting commitments into tasks.
Helps teams build, evaluate, and deploy AI agents as hosted chat apps or through an API and SDK.
Runs open-weight AI models on users' hardware with encrypted remote access and a distributed inference network.
Centralizes AI agent instructions, skills, and coding standards and syncs them to developers' project directories.
A local-first MCP memory server that keeps coding agents' knowledge current across sessions.
A personal AI assistant that remembers context, manages email and calendars, and connects users’ apps and documents.
A local-first context engine that helps developers and AI coding agents search codebases and their history.
Provides an OpenAI-compatible API for running open-weight language and video models in production.
An interactive chef persona model answers questions aloud in real time using ASCII-rendered visuals.
Lets users branch, compare, and organize LLM conversations on an infinite canvas using their own API keys.
A typed database for deterministic agent memory that runs from object storage on small, edge devices.
An SMS-based AI companion that remembers personal details and helps with everyday questions and tasks.
Generates short videos from text, images, and reference media, with audio and editing features.
Runs and governs AI agent fleets in customer-controlled clusters for enterprise software teams.
A macOS AI agent automates tasks across apps, websites, files, and developer tools.
An open specification for building computers that record and verify AI-generated reasoning.
Connects AI assistants to live business data and tools through configurable skill packs.
A community-ranked directory for discovering and submitting AI tools and platforms.
Converts text into speech in multiple languages and lets users download audio files.
