Msty describes private AI for individuals, teams and organizations, with four products connected as one system: Studio, a private AI workspace; Go, for agents; Nexus, a model gateway hub; and Stack, for organizing knowledge. Studio pricing lists a free tier and an Aurum plan billed yearly at $149 per user.
Directory
Search results
Published directory entries matching your search.
A Hugging Face Space by bstraehle that generates a detailed article from a topic. Users enter an OpenAI API key and a topic, and the app produces a comprehensive piece of writing based on that input. It is built with crewAI.
Multi-Agent AI - Deep Research is a Hugging Face Space developed by bstraehle. Users provide an OpenAI API key and a research topic, and the application generates a detailed research article based on the provided input. The space is currently sleeping due to inactivity.
Multi-Agent Article Writer is a Hugging Face Space created by DrishtiSharma. Users enter a topic, and the tool produces a comprehensive AI-generated article based on that input. The space is currently paused.
Multi-Agent Chatbot is a Hugging Face Space developed by yujierachel. The chatbot delivers detailed responses to user questions about machine learning, and supports optional upload of machine learning-related PDFs. The space is currently running.
Multi-Agent Land is a Hugging Face Space developed by build-small-hackathon. It launches the Fishbowl Gradio web interface, loads configuration from a local .env file, operates entirely offline without requiring API keys, and automatically configures relevant settings. The space is currently paused.
An interactive eBook compiling research papers on large language model-based multi-agent systems, organized into multiple chapters and updated with new research. It covers task-solving and social-simulation directions, and was initiated by the ChatDev Group at Tsinghua University.
A GitHub repository with a preliminary implementation of the paper "Improving Factuality and Reasoning in Language Models through Multiagent Debate." It contains code for running arithmetic, GSM, biography and MMLU tasks through multiagent debate, with scripts to generate and evaluate answers. More tasks and settings are stated as forthcoming.
AGI, Inc. builds AGI-0, a small action model, and an agent that sees the screen and acts across any app on Android. It runs on the device, learns preferences over time, and works without APIs or integrations. The agent is described as private by design and works offline and on wearables. A platform is offered for building action agents.
MultiSong Leaderboard is a ranking page on the MVSEP music and voice separation platform. It evaluates multisong audio separation algorithms using metrics including SDR, SI-SDR, L1 frequency, log WMSE, aura STFT, aura MRSTFT, bleedless, and fullness, with rankings updated every three hours. The page lists top-performing algorithms and their scores for separation tasks such as bass, drums, other stems, vocals, and instrumentals.
Murf AI is an AI voice and conversational agent platform. It provides tools to generate human-like speech and deploy conversational agents for use by developers, businesses, and creators. The platform offers a text-to-speech API, supports over 200 voices across 35+ languages, includes voice cloning and video translation features, and provides enterprise-grade security. It is described as trusted by over 10 million developers, businesses, and creators.
Murph.AI presents an enterprise platform for deploying organizations as a service, powered by ExOS on AWS Bedrock AgentCore. Agents are synthesized from behavioral DNA and governed by BOODA doctrine. OrgCloud is described as live, with plans available and deployment in minutes.
Narrow is an AI Sales Agent that handles inbound questions and outbound prospecting, including booking meetings, and is positioned as an alternative to a junior sales rep rather than an SDR tool. The site states it knows the product from day one and takes about 10 minutes to set up. Plans start at $1,500/mo for Starter; Growth is $3,000/mo with 5 agents and 5,000 emails/month.
A library of shared system prompts for creating customized educational GPT agents.
Automate your workflows with AI. Describe your workflows step by step in plain language.
The most lightweight experiment management tool that fits any workflow.
Neurolink is described as the pipe layer of an AI nervous system, providing one interface connecting provider neurons to an application across three inference types: generate, stream, and a calibrated decide via TypeSafe Jev. It lists MCP-native, voice, RAG, memory and file processor features and powers several Juspay projects.
A software tool for easy and comprehensive assessment of predictive power, with support for neuroimaging features. The project is hosted on GitHub and includes sections for project news, overview, long-term goals, and citation information.
Open-source project that provides AI-assisted learning, courses, tutorials, or study support.
Not Human Search scores websites from 0 to 100 on seven agentic signals, including llms.txt, OpenAPI, MCP and Schema.org. It also indexes agent-ready sites and lets users search for services, APIs and tools by machine-readable readiness. Organic rank is said to be based on readiness rather than payment.
Notion is a collaborative workspace for capturing knowledge, finding answers across apps, and automating tasks. It offers block-based docs, databases, AI meeting notes, enterprise search across Notion, Slack, and Jira, and agents for team workflows. Features include wikis, teamspaces, real-time collaboration, data syncs, forms, imports, and mobile apps.
Novu is described as open-source notification and agent communication infrastructure. One API connects AI agents and products to customers across in-app, email, SMS, push, WhatsApp, Slack, Microsoft Teams and Telegram, and an Inbox component can be added to an app. Novu Connect plugs an AI agent into channels such as Slack, Teams, WhatsApp, email and Telegram, starting from templates.
Odysseus is a self-hosted AI workspace for running language models on one's own hardware. It offers chat, autonomous agents, tools and MCP connections, model serving, an email assistant, deep research, model comparison and persistent memory. The project is described as local-first and privacy-first, with no telemetry.
OmniRoute by Cheaper Inference is an open-source AI router that routes requests across providers through one OpenAI-compatible endpoint, with automatic fallback. It accepts OpenAI, Claude, Gemini and Responses API requests at /v1 and ships as a self-hosted gateway with a local dashboard. The catalog covers chat, media, search, local runtimes and cloud agents.