A 3D-controlled image generation tool that allows users to change the camera viewpoint of an uploaded image using an interactive 3D widget and the Qwen-Image-Edit-Plus model.

activity‑frames records your screen locally, compiles raw snapshots into deterministic “activity frames”, and exposes them as compact context blocks or executable scripts for AI agents, dramatically reducing token cost and improving reliability of repeated computer‑use tasks.

A lightweight Python library for building modular, asynchronous, and composable AI pipelines that unify multimodal content processing and streaming.

A desktop interface for OpenClaw AI agents that replaces complex CLI setups with a graphical UI for managing agents, skills, and automated workflows.

A framework and finetuned Llama-3 model for building AI agents capable of browsing the web through instructions and multi-turn dialogue.

A benchmark and agent harness for evaluating LLM-driven agents in finding and exploiting smart contract vulnerabilities.

A reinforcement learning framework for training AI agents to play Pokemon Red, featuring coordinate-based exploration rewards and live training broadcasts.

A Python framework for building single-agent systems with a ReAct loop, tiered tool permissions (L1-L3), and secondary authorization via IM platforms for high-risk operations.

A multi-platform AI coding plan assistant that integrates multiple AI providers and monitors token usage across a browser extension and a macOS application.

A customizable interaction layer that maps AI IDE actions to various hardware devices and voice commands to streamline AI-assisted coding workflows.

A zero-dependency CLI tool that allows AI coding agents to recall previous session history and touched files from local stores, reducing token waste and re-orientation time.

A semantic context search engine for MCP clients that indexes local directories into vector storage to help AI agents find relevant code and documentation.

VPSCI is a large, high‑resolution dataset of vehicle‑pedestrian near‑miss interactions generated by a three‑stage reinforcement‑learning pipeline in the CARLA simulator. It contains ~198 k episodes across eight intersection scenarios, with CSV files logged at 20 Hz and supporting videos. Human studies show the generated interactions are indistinguishable from real‑world footage, making the dataset valuable for autonomous‑driving safety research.

A long-term memory plugin for OpenClaw that uses the cloud-based Supermemory service to automatically capture and recall conversation context and user profiles.

A .NET MAUI cross-platform mobile chat application that provides a unified interface to interact with multiple AI models like DeepSeek, Doubao, and Qwen.

A browser extension for claude.ai that adds folder organization, timeline navigation, and a prompt library to enhance chat management.

An automated trading framework that uses machine learning to predict price movements, featuring a consistent pipeline for offline model training and online real-time signaling.

An agent-first TypeScript admin panel framework that automatically generates a functional UI for managing databases like Postgres, MySQL, and MongoDB.

An end-to-end platform for designing, optimizing, and executing quantum software that transforms high-level functional logic into optimized quantum circuits.

A local-first, self-improving AI testing engine that automates product validation across Android, iOS, and Web by turning natural-language intent into real-device execution.

An executable prompt template file format for Generative AI that decouples prompt engineering from application code across multiple languages and model providers.

A singing voice conversion tool that enables real-time voice changing and high-quality voice cloning with an improved GUI and faster training.

A single SQL query interface for AI agents to access multiple data sources, reducing tool-call complexity and improving accuracy and cost efficiency.

A Python framework for generating adversarial examples, augmenting data, and training robust NLP models to identify and fix vulnerabilities in text-based AI.

A high-performance AI search and intelligence platform that provides dense, sparse, and hybrid vector retrieval for RAG pipelines and AI agent memory.

A JAX library for building and sampling probabilistic graphical models, focusing on efficient block Gibbs sampling and energy-based models.

An architecture-first workflow plugin for AI coding agents that turns large software changes into a spec-driven loop of analysis, decomposition, and adaptive execution.

A collection of AI agent skills and CLI tools for the Neta Art API, enabling agents to generate multimedia, manage characters, and run interactive story adventures.

An accessibility-first operating layer for AI agents that allows them to interact with software using semantic UI structures rather than relying solely on screenshots and pixel coordinates.

A progressive active learning framework for infrared small target detection that enables models to achieve high performance using only single-point supervision instead of full masks.

A distributed social infrastructure network that allows AI agents to communicate, collaborate, and compete on a real-time 3D map without a central server.

A world model architecture for quantitative finance that models market participants as agents in a game to predict denoised equilibrium prices and detect regime instability.

PMB is an open‑source Python library that gives LLM‑based coding assistants a local, SQLite‑backed memory. It automatically indexes code, PDFs, git history, and user‑recorded facts, then injects the most relevant pieces back into the agent via the Model‑Context‑Protocol. The system works offline, offers a hybrid BM25‑+‑vector search (≈35 ms warm latency), provides a visual dashboard, and includes hooks that both recall memory before the model thinks and auto‑write observed actions. Install with `pip install pmb-ai`, run `pmb setup` to wire an agent, and the agent will remember decisions, lessons, and project context across restarts without any API keys or cloud calls.

A Bun and TypeScript-based AI agent for nutrition and healthy diet support featuring RAG, food image analysis, and official health data synchronization.

A training-time alignment framework for reference-to-video generation that improves identity consistency and reference fidelity without adding inference-time overhead.

A verifiable decentralized storage network secured by EigenLayer for AI training data, ML models, and Web3 applications, ensuring data integrity via cryptographic proofs.

A Go-based command-line interface for interacting with OpenAI and other compatible LLMs to generate shell commands, code, and text responses directly in the terminal.

AgentRT is an AI Agent runtime platform that provides a unified orchestration layer for multi-agent cognitive cycles, memory, and security isolation.

An API conversion tool that provides Gymnasium and PettingZoo bindings for popular external reinforcement learning environments like OpenAI Gym and DeepMind Control.

A local-first communication and coordination layer that allows different AI coding agents to synchronize work, claim files, and exchange messages within a shared repository.

A multi-purpose AI agent framework focused on context and attention mechanisms, providing layered memory and dynamic retrieval for long-term companionship, coding, and work.

An agent proxy that enables AI assistants to meta-learn and evolve through real-world conversations using skill injection and asynchronous RL fine-tuning.

A toolkit for converting and running Stable Diffusion models on Apple Silicon using Core ML, featuring advanced weight compression for mobile deployment.

A self-hosted Discord bot that integrates multiple AI providers and local models into one interface, supporting persistent chat history and media generation.

A unified AI model gateway and governance infrastructure that centralizes model access, cost management, and operational monitoring for AI applications and agents.

A production-focused Java library for extracting structured tables from text-based, scanned, and image-heavy PDFs using OCR and table structure detection.

A high-performance Transformers library for PaddlePaddle that enables efficient pre-training and post-training of LLMs and VLMs with extensive support for distributed strategies and domestic AI hardware.

A Python library and command-line utility for extracting summaries from HTML pages and plain texts using various summarization algorithms.