A platform for discovering and installing reusable skills that extend AI agents such as Claude Code, Cursor and Codex. Skills are added with a single command, and a leaderboard ranks skills by install counts.
agent-browser is a command-line interface for headless browser automation, designed for AI agents. It uses a Rust CLI and a Node.js daemon that manages a Playwright browser, and outputs compact text snapshots with element references.
Kyutai TTS is a real-time text-to-speech model suite from Kyutai, released as open source. It includes Kyutai Pocket TTS, a 100 million parameter model that runs on a standard CPU, and Kyutai TTS 1.6B, which begins generating audio before the full input text is received.
Daytona is an infrastructure platform for running AI-generated code in isolated sandbox environments. It provides programmatic APIs for executing commands, managing files, integrating with Git, and deploying virtual desktops.
Ente Photos is an end-to-end encrypted photo storage app available on Android, iOS, web, Mac, Linux and Windows. It is open source, can be self-hosted, and includes on-device face recognition and natural language search.
LiveKit is an open-source framework and developer platform for creating, testing, deploying, scaling and observing AI agents, with a focus on voice, video and physical interaction. It provides real-time communication and observability tools for developers.
LiteLLM is an AI gateway that provides a unified, OpenAI-compatible interface to over 100 large language models. It adds spend tracking, rate limiting, fallbacks and prompt management for teams running multiple models.
Agent TARS is an open-source multimodal AI agent that lets users control and automate web browsing through natural language commands. It can interact with page elements via the browser DOM and is set up locally with an npx command.
Prime Intellect is a platform that aggregates GPU compute across data centers for training and running machine learning models, with single-node and multi-node cluster reservations. It also runs decentralized training projects such as INTELLECT-1 and INTELLECT-2 and hosts reinforcement learning environments.
MindsDB is an AI analytics platform that lets users query data from over 200 connected sources using natural language. It is designed to produce insights and dashboards without moving data through ETL processes.
Memobase is an open-source, cloud-ready memory backend for AI applications that stores structured user profiles and memory events. It lets developers build agents and consumer apps that retain user preferences and interactions across sessions.
MCP-B (Model Context Protocol for the Browser) is a framework that embeds MCP servers in web pages so AI assistants can call a site's functionality directly. It uses existing browser sessions for authentication and is distributed as an npm package and a Chrome extension.
BrowserOS is an open-source web browser built as a Chromium fork that runs AI agents locally on the user's device for tasks such as form filling, scheduling and research. It is released under the AGPL-3.0 license and supports Ollama and existing Chrome extensions.
Kimi K2 is an open-weight Mixture-of-Experts language model with 1 trillion total parameters and 32 billion activated, optimized for agentic tasks such as tool use, coding and mathematics. It is offered in Base and Instruct versions with an OpenAI and Anthropic compatible API.
Director is an open-source, local-first gateway that connects any LLM to multiple Model Context Protocol (MCP) servers. It includes a CLI for managing proxies and connections, a web studio for configuration, and structured JSON request logging.