A tool for batch exporting ChatGPT conversation history from personal, team, and project spaces into JSON or Markdown formats.

An agentic research tool that automates company briefings by coordinating web search and multiple LLMs to produce structured, source-backed reports.

MOSS is an open-source bilingual (Chinese-English) conversational language model with 16B parameters that supports multi-turn dialogue and external tool calling via plugins.

An MCP server that connects LLMs to LogSeq, enabling AI agents to read, write, and semantically search a personal knowledge base.

officeParser is a TypeScript‑ready Node.js (and browser) library that parses many office file types (DOCX, PPTX, XLSX, ODT/ODP/ODS/ODG, PDF, RTF, CSV, Markdown, HTML, EPUB) into a strict Abstract Syntax Tree. From the AST you can extract layout‑faithful plain text, convert to other formats (DOCX, ODT, Markdown, HTML, CSV, RTF, PDF, EPUB), run OCR on embedded images, perform mail‑merge templating, and generate RAG‑ready chunks for LLM pipelines. It supports password‑protected files, native PDF generation, a CLI, and an interactive web visualizer.

An experimental framework for benchmarking LLMs and AI agents by having them autonomously solve CTF challenges and security labs across multiple platforms.

An AI-powered penetration testing tool that uses LLMs to automatically identify login form selectors and execute automated brute-force attacks.

HarnessX is a composable agent harness foundry that decouples model selection from behavior logic, allowing developers to evolve agent performance through automated harness optimization and RL fine-tuning.

An open-source framework that gives AI agents a mobile body, enabling them to control Android and iOS devices via a unified tool surface and MCP server.

An AI coding assistant skill that automates the creation, compilation, and pedagogical review of academic Beamer LaTeX presentations from research papers.

A simple LLM client for Emacs that allows users to interact with multiple AI models and backends directly within any buffer.

A lightweight RAG development framework based on the Model Context Protocol (MCP) that enables low-code orchestration of complex retrieval-augmented generation workflows.

A local web research assistant that uses LLMs via Ollama or LMStudio to iteratively search, summarize, and reflect on topics to produce a comprehensive cited report.

An AI-driven knowledge base system that converts Git repositories and local directories into structured documentation, searchable wikis, and MCP-enabled chat assistants.

A lightweight SDK providing reference implementations for Hashgraph Consensus Standards to enable trustless AI agent communication, identity verification, and decentralized data storage on Hedera.

An AI-powered mistake management system that helps students organize, analyze, and review wrong answers through automated tagging and similar-problem generation.

A Codex-only workflow for capability-routed software delivery that automates planning, implementation, and verification using risk-based agent routing.

An LLM-powered platform that converts unstructured documents like PDFs and images into structured JSON data via natural language prompts.

A zero-code platform for auto-generating production-grade AI agents using natural language prompts, featuring multi-agent collaboration and a plug-and-play tool ecosystem.

A Python SDK for building agentic applications that follow the Agent2Agent (A2A) Protocol for standardized inter-agent communication.

A structured execution framework for Claude that enforces a stage-mapped, multi-agent delegation process with mandatory failable verification to prevent errors in large tasks.

A library for building multimodal AI applications and agentic teams, featuring a unified provider interface, multi-agent debate frameworks, and a knowledge graph with sleep/dream lifecycles.

An MCP server that enables LLM agents to interact with the Lean theorem prover via LSP, providing tools for proof state analysis and theorem searching.

An Obsidian plugin that uses local embeddings to automatically surface semantically related notes, helping users discover connections in large vaults without manual tagging.

A self-hosted personal AI OS that integrates persistent memory, task automation, and coding agents across multiple apps and interfaces.

A modified YouTube client that uses JavaScript injection and Google Gemini to provide AI video summarization, ad-blocking, and advanced download tools.

A local coding agent that enhances compact open models with planning, sandboxed verification, and iterative repair to perform software engineering tasks on consumer hardware.

A self-hosted personal agent workbench that bridges AI coding engines like Codex and Kimi Code to messaging apps like Telegram and Slack for mobile-friendly AI development.

A memory enhancement plugin for SillyTavern that uses structured tables to provide AI characters with long-term memory of events, settings, and items.

An MCP server that connects AI assistants to the Hevy workout tracking app, allowing users to analyze training progress and manage workouts via natural language.

An AI-powered AstrBot plugin that analyzes group chat activity to generate visual reports and creative comics across QQ, Telegram, and Discord.

A lightweight framework using a hierarchy of AGENTS.md files to give AI agents precise project context and prevent blind edits during coding.

A mod for Slay the Spire 2 that exposes game state and actions via a REST API and MCP server, enabling AI agents to fully automate gameplay.

An open-source workbench for Generative Engine Optimization (GEO) that helps brands diagnose and improve their visibility in AI-powered search engines.

An MCP server that enables AI agents to convert PDFs into structured data and generate new documents using the Docling library.

An open-source document intelligence platform that transforms document repositories into programmable citation graphs with AI agents, human annotation, and MCP server support.

An AI-powered decentralized learning community that creates personalized knowledge bases and adaptive practice questions based on a user's learning trajectory.

A collection of public AI agent skills that extend agent capabilities with tools for dynamic workflows, Claude Code plugin development, and personalized learning.

An AI browser agent that uses a Chrome extension and MCP connector to operate websites concurrently and access data behind logins to deliver finished work.

A desktop client that allows users to send prompts to multiple AI bots concurrently to compare their responses and find the best result.

A collection of specialized AI agent plugins called Skills that extend the capabilities of AI assistants to better support HashiCorp Terraform and Packer.

A set of components and bundles for PHP applications to integrate AI capabilities, providing unified interfaces for AI platforms, agents, and AI-specific data storage.

A curated collection of plugins for Open WebUI that adds interactive visualizers, automated system cleanup, and enhanced model capabilities like vision bridging for text-only models.

A production-ready AI agent orchestration framework featuring 66 self-learning agents, advanced attention mechanisms, and a self-optimizing neural architecture to reduce costs and improve swarm coordination.

A production-ready MCP server that connects AI assistants to Nextcloud, enabling LLMs to perform CRUD operations on notes, calendars, and files via natural language.

A self-hosted codebase understanding tool that combines AI-powered natural language querying with fast cross-repository search and IDE-level code navigation.

A collection of demonstration applications showcasing various ways to build AI-powered agents and apps using the Claude Agent SDK.

AutoNovel is an open‑source web service that automatically translates light‑novel text using machine translation and shares the results. It can be run locally with Docker Compose, though the authors warn that personal deployment isn’t officially supported.