PySpur is a visual playground for AI engineers to build, debug, and deploy AI agents, solving the problems of prompt tweaking and workflow invisibility.

An interaction control harness for customer-facing AI agents that uses dynamic context engineering to ensure consistent, compliant, and brand-aligned behavioral control.

A persistent AI companion and agent runtime written in Rust that integrates long-term memory, computer use, and scheduled background work.

A Raycast extension for quickly looking up words and translating text across 48+ languages using various translation services and LLMs.

A reverse-engineered implementation that allows the macOS-only Claude Desktop Cowork feature to run natively on Linux x86_64 without a VM.

A single-binary Go client for NotebookLM that provides a scriptable CLI, an interactive chat client, and an MCP server for AI agents.

An open-source Notion alternative that provides a collaborative, AI-enhanced workspace for knowledge bases, project management, and documentation.

An AI-powered Obsidian plugin that transcribes audio and YouTube videos, organizes raw notes, and enables vault-context chat.

An AI-powered learning coach that integrates with Claude Code and Codex to accelerate technical mastery through spaced repetition, personalized syllabi, and active practice.

A no-code development platform for creating AI-powered chatbots and conversational apps using a drag-and-drop visual interface and LLM integration.

A comprehensive suite of benchmarks, frameworks, and models from Alibaba designed to enhance AI agents' capabilities in hierarchical reasoning, deep-and-wide information seeking, and self-evolving memory.

A self-hosted AI agent orchestration platform that allows operations teams to visually design, manage, and audit agent workflows while engineers handle the system integrations.

A library that enables developers to build natural language interfaces by replacing prompt engineering with schema engineering, ensuring LLM responses are structured and validated against defined types.

An MCP server that connects AI assistants to South Korea's MOLIT real estate API to provide live transaction data and financial investment simulations.

A multilingual visual dashboard for the Hermes agentic orchestration system that makes multi-agent delegation and kanban task tracking visible and manageable from a browser.

A collection of ~100 specialized skills for Claude Code that automate complex workflows across development, research, media generation, and personal analytics.

An AI-powered tool that transforms topics or files into interactive, visual mind maps using LLMs and a custom SVG rendering engine.

An agentic AI framework for designing and orchestrating multi-agent systems with distributed execution environments, hybrid memory, and built-in safety guards.

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 MCP server and Firefox extension that lets AI assistants securely manage tabs, search history, and read webpage content with explicit user consent.

An open-source agent-based framework for chatting with data and RAG, enabling users to generate data pipelines and visualizations via natural language.

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

A local-first stack that turns coding agents into personal AI assistants for work by leveraging existing user permissions and tool access to bypass corporate IT constraints.

An LLM-first wiki knowledge base that automatically converts team chat history from Slack, Discord, and Teams into a structured, cited wiki and QA agent.

An enterprise accelerator for building agentic RAG solutions on Microsoft Foundry, featuring Zero-Trust security and multi-source data retrieval via Foundry IQ.

A voice-activated, 100% local LLM agent for Raspberry Pi that can be extended with custom tools to automate hardware actions.

A local-first long-term memory system for AI agents that automatically captures and updates user preferences and facts across sessions to eliminate AI amnesia.

Darts is a Python library for time‑series forecasting and anomaly detection. It unifies classic statistical models and deep‑learning models behind a scikit‑learn‑style API, supports probabilistic forecasts, multivariate series, covariates, back‑testing, and integrates with PyTorch Lightning and MLflow.

DemoGPT is an open-source framework that automatically generates LangChain code and Streamlit apps from user instructions and provides a library of tools for building AI agents with RAG capabilities.

A collection of structured skills for AI agents that implements inner and outer feedback loops for automated verification, self-healing, and cross-session learning.

An offline-first PWA for children's English learning that uses a gamified map and pre-generated AI audio for interactive reading and exercises.

A gamified agent-building platform that uses a 3D spatial interface to let beginners easily design and deploy AI agents, with integrated WeChat connectivity.

A comprehensive cross-platform client for the Xiaozhi AI assistant, supporting real-time voice and text interaction across mobile, desktop, and AI hardware terminals.

An open-source Agent Skills toolkit for Xiaohongshu content research, creation, and quality control that breaks the production process into 15 modular, traceable skills.

A Go‑based command‑line client that lets you chat with OpenAI’s GPT‑3.5‑turbo or GPT‑4 (or Azure OpenAI) from the terminal, with configurable prompts, history, and extensive key bindings.

A professional financial skill set for Claude adapted for the Chinese A-share market, integrating Wind, iFind, and AkShare for automated financial analysis and reporting.

A lightweight web GUI for multiple LLMs that adds features like web search, document-based Q&A, and support for both API and locally deployed models.

An LLM-driven data analyst that writes and executes Python code in a persistent kernel, verifying its own results through a reproduction run before reporting them.

An Obsidian plugin that integrates multiple AI providers (Claude, Gemini, Codex, Antigravity) into a sidebar, featuring inline diff editing and specialized academic research tools.

An open-source dataset for the Moroccan dialect (Darija) providing human-curated and synthetic parallel data for English translation and NLP tasks.

A native Android and iOS client for DeepSeek Harness that allows users to remotely manage AI agents, workspaces, and real-time conversations via a mobile gateway.

A Python library that converts unstructured documents into validated Pydantic objects using LLMs and customizable document loaders.

A research codebase for Alibaba DAMO Academy's conversational AI projects, featuring high-performing Text-to-SQL and dialogue systems.

A VS Code extension that provides AI-powered ghost-text code completion and code attribution using various LLM backends like Hugging Face and Ollama.

A collection of robust training recipes and scripts to continue pretraining and align language models with human and AI preferences using techniques like DPO and ORPO.

KBLaM is a method for augmenting LLMs with external knowledge using trained adapters that transform knowledge bases into tokens, avoiding external retrieval and quadratic scaling issues.

A trust-based prompting framework for AI agents that replaces fear-driven motivation with cognitive elevation to increase debugging depth and honesty.

An Android application that provides a GUI for running AI agents via OpenClaw, eliminating the need for a terminal or CLI setup.