A Python package for extracting structured, ontology-grounded information from text using LLMs, preventing hallucinations by validating identifiers against real-world ontologies.

A prompt-based skill for AI agents that simplifies jargon-heavy or overly formal responses into plain, casual language using the /bro command.

A plugin that connects AnySearch to DeepSeek Harness, enabling AI agents to perform real-time web and vertical searches and retrieve cleaned URL content.

A prompt library and agentic SDLC framework for GitHub Copilot that provides specialized agents, reusable prompts, and coding instructions to make AI-assisted development repeatable and scalable.

An open-source framework that provides a unified interface for researching and evaluating web agents across multiple benchmarks and open-ended web tasks.

An AI agent orchestrator that monitors issues in Linear, GitHub, GitLab, or Slack and uses AI coding agents to resolve them in isolated Git worktrees.

A system-wide AI text assistant for Android that allows users to transform, fix, or translate text in any app using inline trigger commands.

A Go implementation of the Microsoft Agent Framework for building production-grade AI agents and multi-agent workflows with graph-based orchestration.

A visual drag-and-drop builder for creating and deploying AI agents and workflows without writing code.

A framework for building and deploying serverless AI agents as code, providing a managed cloud environment and CLI for rapid development.

An AI-powered tool that converts EPUB and PDF ebooks into structured mind maps and text summaries to make complex books easier to digest.

A library that unifies the training, inference, and evaluation of diffusion language models, providing scalable pipelines and recipes for converting AR models into diffusion models.

An MCP server that allows Claude and other AI models to control a local computer via keyboard and mouse automation.

A Go SDK for building and interacting with agentic applications that follow the Agent2Agent (A2A) Protocol for standardized communication.

A multi-provider AI chat client for Android that allows users to interact with various LLMs and deploy on-device agents with tool-calling capabilities.

OWL is a multi-agent collaboration framework for real-world task automation that ranks #1 among open-source frameworks on the GAIA benchmark.

A marketplace of MCP servers and skills for Claude Code that integrates life sciences research tools, academic databases, and bioinformatics workflows into the AI assistant.

A high-accuracy language detection library that identifies the languages of text snippets, specifically optimized for short phrases and single words.

A Next.js application that integrates E2B's desktop sandbox with OpenAI's Computer Use API to create an AI agent capable of operating a virtual computer via natural language.

An AI-driven presentation platform that transforms topics or documents into professional, editable PPTs with automated outlining, research, imaging, and video export.

An AI-powered cybersecurity tool that automates threat data analysis, CVE exploit creation, and bug fixing in JIRA tickets.

A modular, local-first AI agent framework designed for token efficiency and personal life management, supporting multiple interfaces and sandboxed shell execution.

A UCI-compliant chess engine that uses neural networks to play and evaluate chess positions, supporting a wide range of hardware backends for optimized performance.

An MCP server that enables AI assistants to search Airbnb listings with advanced filtering and retrieve detailed property information.

A CLI and TUI for HEY email and calendar that allows users and AI coding agents to interact with their communications and scheduling directly from the terminal.

An agentic skill for Claude Code and OpenAI Codex that transforms Markdown into commercial-grade e-book PDFs using professional typesetting rules and a rigorous 17-gate quality control system.

A control-room framework for language-agent societies that allows users to observe, pause, and intervene in AI agent simulations in real-time.

A fully localized Chinese distribution of OpenClaw, providing a translated CLI and Dashboard for managing a personal AI assistant platform.

MineContext is a proactive, context-aware AI partner that captures screen activity and digital content to automatically generate summaries, to-do lists, and insights.

Tmax is a framework for training and evaluating terminal-using AI agents, featuring a synthetic data generation pipeline and a specialized training recipe.

An open-source, on-device system-wide tab-autocomplete utility for macOS that uses a local LLM to provide ghost-text predictions.

An experimental workspace for large-scale recommendation systems that unifies sequence modeling and feature interaction for conversion rate prediction.

A self-hosted AI novel writing platform that provides a structured workflow for managing outlines, characters, and world-building to ensure consistency in long-form storytelling.

A Neovim IDE integration for Claude Code that implements a WebSocket-based MCP protocol to bring Anthropic's AI coding assistant into the editor.

A communication layer for Pi agent sessions on the same machine, enabling 1:1 messaging and coordination between parallel agents or between subagents and supervisors.

An open-source agent operating system that uses isolated WorkSpaces, white-box memory, and smart model routing to manage long-running, multi-project productivity tasks.

An agentic research platform that automates planning, retrieval, and cited answers across the web, academic papers, and financial data.

An on-device AI system for macOS that builds a private markdown knowledge base from your personal data to provide proactive task automation and computer-use agents.

An AI coding agent that prevents reasoning degradation by isolating a lead orchestrator from ephemeral, disposable subagents that handle the noisy execution steps.

An AI-powered penetration testing assistant that automates security assessments using agentic workflows and isolated cloud execution.

An advanced OCR pipeline that uses LLMs to correct errors in raw Tesseract OCR output and transform it into high-quality, formatted Markdown documents.

A lightweight coding agent designed to eliminate context bloat, enabling efficient operation on local LLMs and remote APIs while providing tools to read, write, and execute shell commands.

A Model Context Protocol (MCP) server and CLI tool that connects AI agents to real-time South Korean retail inventory, convenience store data, cinema schedules, and fuel prices.

MiroFlow is an open-source research agent framework for multi-step internet research and complex reasoning tasks, such as future event prediction.

A secure, open-source terminal coding agent written in Rust that provides a sandboxed runtime and durable sessions for autonomous AI development.

A local MCP server that enables AI assistants to read, search, and edit notes within an Obsidian vault directly via the file system.

An official MCP server that integrates Perplexity's real-time web search, reasoning, and research tools into AI assistants and IDEs.

An open-source AI coding agent that lets users edit frontend source code directly from the browser by clicking elements and describing changes in plain English.