A graph-centric framework for orchestrating multi-agent systems that uses "Vibe Graphing" to turn natural-language intent into executable agent workflows.

A reinforcement learning framework for multi-agent LLM systems that uses Conflict-Aware Policy Optimization to train agents without flattening execution sequences.

Polis is an AI-powered sentiment gathering platform that maps high-dimensional opinion spaces to scale public deliberation more organically than surveys or focus groups.

A multi-agent personal assistant that builds long-term memory through screen observation and natural conversation, featuring a specialized six-component memory system.

An open-source .NET framework for building AI bot platforms that allows enterprise developers to integrate LLMs and multi-agent systems into business applications.

A free, lightweight desktop application that provides a unified interface for interacting with multiple LLM providers and local models using your own API keys.

An open-source, agent-first IDE and universal AI gateway that allows developers to use any LLM to power autonomous agents for coding tasks.

A macOS menu bar app that uses AI to generate, build, and export native SwiftUI applications from simple text descriptions.

Anything is a Windows/macOS desktop app that locally indexes documents (HWP, DOCX, PDF, images, etc.) and lets you search by content, filename, or natural‑language query. Optional AI Q&A and summarisation use Gemini or OpenAI‑compatible endpoints; otherwise the tool works fully offline. Features include fast full‑text search, real‑time folder monitoring, preview with original layout, OCR, markdown export, file‑compare, and a “Lite” build for air‑gapped environments. It is built with React/Tauri on the front‑end and Rust‑based parsers/indexers on the back‑end, and is released under a Business Source License.

An open, cross-canon Buddhist knowledge infrastructure that uses RAG and LLM-verified alignments to provide cited, verifiable AI answers from over 600 sources.

A serverless, AI-powered personal bookmarking system that uses RAG for automatic summarization and tagging across web, mobile, and browser extensions.

A browser extension that provides a quick-access gallery of AI prompts for Gemini and other websites, allowing users to insert pre-defined prompts into input fields instantly.

A high-performance Rust implementation of the Jieba Chinese word segmentation algorithm for splitting text into words.

A terminal-native coding agent optimized for local LLMs (8B-35B parameters) that uses intelligent context management and tool routing to enable reliable coding on consumer hardware.

A writing skill for AI agents that implements ten restrained narrative techniques to replace sentimental AI prose with concrete, action-oriented storytelling.

A browser-based interface for Claude Code and Codex that allows you to supervise and control AI agents running on your machines from any device.

A LangGraph template for implementing a ReAct agent that iteratively reasons and executes tool-based actions to solve complex user queries.

A library and MCP server that connects AI agents to Todoist, enabling LLMs to access and modify tasks and account data.

A multi-agent simulation framework that uses LLMs to create interactive story worlds, featuring the ability to generate entire simulated environments from a single natural language prompt.

A lightweight, single-binary coding agent harness written in Go that provides a unified interface for 30+ AI providers and built-in tools for filesystem and shell interaction.

An AI-powered equity research framework that transforms AI agents into institutional-grade analysts by enforcing rigorous valuation, forensic accounting, and industry-specific research protocols.

A powerful meme management plugin for AstrBot that enables AI bots to intelligently send, automatically collect, and semantically retrieve memes during conversations.

A starter template for building AI applications with LangChain.js and Next.js, featuring implementations for streaming chat, RAG, and agentic workflows.

An AI software engineer that automatically picks up tickets from GitHub, Jira, or Linear, implements the code, and opens pull requests for review.

Obsidian desktop plugin that lets you write markdown, have a local AI Agent format it for WeChat, preview the result side‑by‑side, and then create a WeChat public‑account draft via the external `md2wechat` CLI.

An Ableton MCP server and REST API that allows users to control Ableton Live using natural language via AI assistants or custom scripts.

A Chinese‑language, hands‑on tutorial that walks users from basic PyTorch concepts to a full GPT‑style implementation, then extends the lessons to modern architectures (GLM‑4, Llama 3, RWKV, MiniCPM). Includes notebooks, training scripts, and exercises, all under Apache 2.0 / CC‑BY‑NC‑SA licensing.

An AI-powered workspace that converts scientific papers, notes, and data into editable PowerPoint, Excel, Word documents, and professional visual assets.

A token-efficiency skill for coding agents that reduces API costs and token usage by teaching agents more efficient lookup and polling habits.

An autonomous multi-model AI agent swarm for offensive and defensive security automation, designed to solve CTFs and perform penetration testing by coordinating diverse LLMs via a shared blackboard.

An AI-powered homework assistant that uses LLMs to solve problems from images and PDFs, featuring an ergonomic, keyboard-centric interface and support for visual diagrams.

A Chrome extension that adds a native AI layer to the browser, integrating multiple LLM providers and enabling agentic browser control and external MCP tool support.

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

An open-source engine that adds a persistent learning loop to AI agents, allowing them to learn from mistakes and improve via a dynamic 'Skillbook' of strategies without fine-tuning.

An open-source reference app for building and running background coding agents on Vercel, featuring a decoupled agent runtime and isolated sandbox environments.

A flexible, lightweight framework for orchestrating multiple AI agents across Python, TypeScript, and Swift, featuring intelligent routing and on-device execution for Apple platforms.

A unified text-to-text transformer framework that treats all NLP tasks as string-to-string problems, enabling large-scale pre-training and fine-tuning.

A governed, local-first agent runtime for Python that provides strict permission controls, persistent memory, and tool connectivity via MCP/ACP.

A multi-market stock screening and analysis platform that combines technical scans, market breadth indicators, and AI-powered theme discovery and research.

A collection of spec-compliant agent skills and templates that provide AI agents with domain knowledge and structured workflows for Java and Maven development.

Yank Note (yn) is a cross‑platform Electron markdown editor that stores notes as plain `.md` files. It integrates AI copilot capabilities (OpenAI, Ollama, Gemini, etc.) for text and image generation, plus an OpenCode AI Agent for coding help. Features include VS Code‑like Monaco editing, live preview, version history, runnable code blocks, rich embeds (PlantUML, Mermaid, LaTeX, etc.), client‑side encryption, plug‑in extensibility, and multi‑format export via Pandoc.

An open-source, local-first note-taking app for Mac and iOS that uses Markdown files and supports wiki links, local search, and optional AI querying over personal notes.

An AI agent skill that researches and converts travel itineraries into polished, mobile-first, single-file HTML pages with interactive maps and booking reminders.

A graph-based knowledge base that uses LLMs to compile raw documents into an interlinked wiki and knowledge graph for shared human-AI memory.

An autonomous AI workflow that transforms natural language game ideas into playable 2D Godot engine prototypes, handling everything from GDD planning to implementation and visual QA.

An enterprise-grade toolkit for building, observing, and optimizing AI agents across various frameworks, enhancing their speed and accuracy through performance primitives and instrumentation.

A Calibre plugin that translates ebooks into specified languages using various translation engines like ChatGPT, Gemini, and DeepL.

A RAG-based system that converts Bilibili video collections into a conversational knowledge base by transcribing audio to text and indexing it for semantic search.