HiRAG is a Retrieval-Augmented Generation framework that uses hierarchical knowledge to improve the quality and comprehensiveness of LLM responses compared to standard RAG.

A controllable autonomous RAG agent that uses a deterministic graph and adaptive planning to solve complex, multi-hop questions from custom datasets while preventing hallucinations.

A private, local control plane for AI agents that manages routing, verification, and governance across multiple AI vendors to ensure users maintain full control and data ownership.

A local AI Agent platform that implements an "AI as Code" philosophy, allowing project-specific AI assistants to be configured, versioned, and managed locally via files.

A domain-specific programming language for prompting models that uses type inference to automatically generate JSON schemas and build complex prompt chains.

A Chrome extension AI web agent that runs entirely on-device using WebGPU, allowing users to automate web tasks privately and for free without cloud APIs.

An MCP-compatible bridge that lets LLMs securely interact with ERPNext sites to manage invoices, customers, and workflows using natural language.

A minimal implementation of Recursive Language Models (RLMs) that allows LLMs to handle arbitrarily long prompts by interacting with data through an external REPL and recursive sub-agents.

An open-source meeting copilot that provides real-time AI assistance via a stealth overlay and automated post-call summaries using local storage and BYOK API keys.

A stable, low-latency multi-agent search framework featuring a 5-layer hierarchical memory RAG stack that improves over time as it archives successful answers.

A collection of practical code samples and templates for building agentic workflows and AI solutions using Azure AI Foundry and Azure OpenAI Service.

An open-source AI chatbot platform that integrates multiple LLMs and the Model Context Protocol (MCP) to provide advanced automation, visual workflows, and custom agents.

An AI agent development framework for Laravel that allows developers to create and maintain AI agents using an Eloquent-like API and Laravel-style tooling.

A Model Context Protocol server that enables AI assistants to download and read YouTube subtitles using yt-dlp for video summarization and analysis.

A Discord bot that transforms servers into collaborative LLM frontends, using Discord's reply chains to manage conversation history without a database.

An MCP server that enables AI language models to interact with YouTube by providing tools to search videos, retrieve transcripts, and analyze channel data.

An open-source project management platform that uses conversational AI and browser automation to execute tasks and manage workflows via natural language.

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

A TypeScript framework for building governed, durable AI agents that separates reasoning from execution via a Production Harness and DomainPacks.

An AI-powered headless CMS for personal blogs and creator websites, featuring a core server, admin dashboard, and native iOS client.

An AI agent harness that can build, evolve, and operate its own custom SaaS tools through a system called Living UI to automate complex workflows.

An agentic finance toolkit that enables AI agents to manage wallets, execute payments, and perform investment strategies using blockchain infrastructure.

An open-source agentic AI toolkit and Vietnamese NLP library that provides multi-provider LLM support and specialized text processing tools for the Vietnamese language.

A command-line productivity tool that uses LLMs to generate shell commands, code snippets, and documentation directly in the terminal.

An AI-native web OS for building and running portable websites and business applications with integrated AI creation, hosting, and content management.

A set of AI skills for Claude Code and OpenAI Codex CLI that automatically generates privacy policies and terms of service compliant with Korean, EU, US, and Japanese laws.

SkVM is a compilation and runtime system that makes LLM agent skills portable and optimized across different models and agent harnesses.

Icebreaker is a local AI chat application built with Rust and iced that uses llama.cpp to run Hugging Face models locally.

MotionLCM is a research codebase for real‑time, text‑conditioned human motion generation. It uses a latent consistency model for one‑step inference and a Motion ControlNet to incorporate explicit joint trajectories, supporting motion reconstruction, text‑to‑motion, and controllable motion synthesis. The README provides conda setup, data preparation (HumanML3D), pretrained model download, demo commands, rendering with SMPL/Blender, and full training instructions via YAML configs.

An Obsidian plugin that enables AI text generation and multimodal analysis using a tag-based trigger system across multiple AI providers.

An LLM-powered agent that automates Google Dorking for bug hunting and penetration testing to identify security vulnerabilities and sensitive information disclosures.

A Dify workflow that replicates Deep Research functionality to generate long-form, structured research reports using multi-source retrieval and multi-model collaboration.

A set of AI agent skills and Python scripts designed to automate U.S. utility patent auditing, simulated USPTO examination, and adversarial design-around testing to reduce legal fees.

A comprehensive guide and implementation for building, scaling, and productionizing RAG-based LLM applications using the Ray framework.

A terminal AI assistant that turns Apple Health export data into a conversational analysis tool, supporting both local and cloud LLMs for private health metric tracking.

An AI-powered analytical framework that replaces simple chat answers with a suite of "instruments" and workflows to examine the nuances, evidence, and assumptions of complex questions.

An intelligent desktop app for voice, writing, and proactive work that integrates with various apps to manage tasks and and polish voice dictation.

An automated multi-platform operation system for managing multiple social media accounts, featuring AI-driven content creation, scheduled publishing, and automated engagement.

An AI-powered cryptanalysis tool that uses brute-force computation to find statistically significant patterns between Donald Trump's social media posts and stock market movements.

A world-champion Shogi AI engine that provides a high-performance search and evaluation framework compliant with the USI protocol.

A modular sim racing administration tool that provides AI-powered race assistants, telemetry analysis, and hardware automation to help drivers manage races and strategy.

A multi-platform AI translator and text processor that provides translation, polishing, and summarization across 55 languages using LLM providers.

A Microsoft Word add-in that integrates AI and agents to generate, translate, and directly manipulate document content and formatting.

An open-source, AI-native desktop email client that uses Claude to automatically triage, prioritize, and draft emails based on a user's learned writing style.

A cross-platform personal GUI assistant that automates tasks on desktop, Android, iOS, and HarmonyOS using a self-evolving memory and skill system.

An agentic AI coding assistant for Neovim that enables autonomous feature development and secure execution via OS-level sandboxing and Docker sub-agents.

A Gemini CLI extension that enables command-line management of Google Workspace apps like Docs, Drive, and Calendar using natural language.

An Obsidian plugin that integrates Gemini and other AI models to provide an agentic experience for note-taking, featuring semantic vault search, automated tasks, and direct file manipulation.