A collection of validated Docker Compose recipes and tooling for serving LLMs locally on RTX 3090 GPUs, optimizing for throughput and context window stability.

A code-free visual web crawler and browser automation tool that allows users to design and execute data collection tasks through a point-and-click interface.

A high-performance neural network inference framework optimized for mobile, embedded, and desktop deployment with no third-party runtime dependencies.

An experimental llama.cpp fork that introduces Variable Bit-Rate KV cache quantization and Trellis-Coded Quantization to maximize context length and quality on VRAM-constrained GPUs.

A DeepSeek Harness plugin that lets you use ChatGPT, Claude, Grok, Copilot, and Antigravity subscriptions as LLM providers without needing API keys.

MNN is a lightweight, high-performance deep learning framework designed by Alibaba for efficient model inference and training on mobile, embedded, and IoT devices.

A professional multi-account manager for Google Gemini and Claude that automates account switching and provides a local API proxy to bypass quota limits.

A framework for automatically searching and optimizing the code-based scaffolds (harnesses) surrounding a fixed AI model to improve task-specific performance without retraining.

An iOS location services research and testing framework that simulates geographical locations by intercepting Apple's location service responses via a local or third-party proxy.

A hardware-aware LLM recommendation tool that ranks the best HuggingFace models based on your specific GPU/CPU/RAM and real-world benchmark performance.

A unified indexing system that makes session histories from various AI coding agents queryable by both humans and AI agents via a CLI and desktop app.

A toolkit that connects AI coding agents to MATLAB via an MCP server and curated skills, preventing hallucinations and enabling agents to write and execute idiomatic MATLAB code.

A high-performance web research tool for AI agents that bypasses bot detection using native Chrome TLS and provides keyless search and token-optimized content extraction.

XRAG is an open‑source Python framework that benchmarks the individual components of Retrieval‑Augmented Generation (RAG) pipelines. It offers modular plug‑ins for retrievers, embeddings, LLMs, and orchestrators, supports traditional IR metrics plus LLM‑based quality scores, provides a CLI (`xrag-cli`) and a Web UI, and can run as a REST service. Install via PyPI, configure with `config.toml`, and use commands like `xrag-cli run`, `xrag-cli webui`, or `xrag-cli api` to evaluate or serve RAG systems.

A Rust-based MCP server and desktop Studio for AI-native ontology engineering, enabling LLMs to build, validate, and govern RDF/OWL knowledge graphs.

An official Model Context Protocol (MCP) server that enables AI applications to start, run, and analyze MATLAB code.

A system utility that tracks and displays AI plan usage and reset timers for multiple LLM providers across status bars, a TUI, and CLI.

A high-efficiency pretraining framework that allows users to pretrain 1B parameter foundation models from scratch with significantly reduced compute and data requirements.

An agent-first computational platform that allows AI agents to offload hard optimization and decision problems to an accelerated, verified execution engine.

An AI-powered penetration testing engineer for authorized security assessments that automates the discovery of business-logic flaws and cloud misconfigurations across global and Chinese cloud providers.

An enterprise-grade, self-hosted registry for publishing, discovering, and managing reusable AI agent skill packages with built-in governance and versioning.

A multi-platform video distribution tool that enables batch publishing and automated uploads to 8 major social media platforms via GUI, CLI, and HTTP API.

A framework for creating repeatable AI software development workflows by moving the control plane from prompts to deterministic Python code, featuring gated agent phases and real-time observability.

A high-performance, GPU-rendered SSH client and remote operations workspace written in Rust that integrates AI assistance, SFTP, and remote desktop tools.

A fast, flexible LLM inference engine written in Rust that supports multimodal models, agentic tool execution, and OpenAI/Anthropic compatible APIs.

A browser-based API tool that lets AI agents use your real browser session to access websites and bypass anti-bot protections without API keys.

A high-performance LLM inference engine optimized for agentic workloads, featuring a split C++ control plane and Python execution plane for maximum speed and usability.

An open-source toolkit for optimizing and deploying deep learning models across CPU, GPU, and NPU hardware to boost inference performance.

A Rust-driven Python API for the TongdaXin quantitative data client, providing high-performance access to A-share market quotes, K-lines, and company financial data.

A developer tool for inspecting and debugging Model Context Protocol (MCP) servers via web, CLI, and TUI interfaces.

EvalScope is a Python‑based, all‑in‑one evaluation framework for LLMs, vision‑language, embedding, and agent models. It runs dozens of benchmarks, provides stress‑testing (latency, throughput), supports multi‑turn agent loops with tool calling, and visualises results in an interactive web dashboard. Install with `pip install evalscope` and evaluate a model via a single CLI command or a few lines of Python.

A curated collection of portable skills and plugins for AI coding agents to perform specialized .NET development tasks like migration, debugging, and package management.

A context engineering layer for AI coding agents that compresses inputs and shell outputs to reduce token costs and extend context windows.

An autonomous improvement engine for AI coding agents that uses a loop of modification, mechanical verification, and git-based rollbacks to optimize code and systems.

A deployment recipe for serving the DeepSeek‑V4‑Flash‑Vision‑Exp model (1 M‑token context, image support) on a two‑node DGX Spark cluster using vLLM, DSpark speculative decoding, and NVIDIA‑optimized KV cache. Includes Docker images, environment‑variable configuration, optional NFS weight sharing, and many performance knobs.

A Claude Code plugin that queries multiple AI coding agents in parallel to provide side-by-side comparisons and a synthesis of consensus and divergence for technical decisions.

A TypeScript and JavaScript SDK that makes functions durable by persisting progress, retrying failed steps, and allowing workflows to suspend without using compute.

An open-source low-code platform for building internal tools and dashboards that uses AI and a visual builder to connect to existing databases and APIs.

A secure and elastic infrastructure runtime that provides isolated sandboxes for executing AI-generated code and managing AI agent workflows.

A deterministic scanner that measures the and scores the maturity of the infrastructure (rules, guides, and guardrails) surrounding AI coding agents to improve their reliability.

A hardware dashboard (ESP32 + touchscreen) that displays Claude Code usage live over Bluetooth, with Clawd animations and physical buttons for voice-mode shortcuts.

An open-source relational database that provides MySQL compatibility and advanced features like native vector search and pluggable storage engines.

A collection of platform-agnostic Agent Skills focused on context engineering to optimize how AI agents manage their limited attention budget and context windows.

A collection of human-reviewed instruction sets (skills) for AI agents to ensure they produce idiomatic, secure, and high-performance Go code.

A remote control hub for AI coding agents that allows users to manage sessions, approve requests, and run commands via mobile apps or web interfaces.

A toolkit that enables AI agents to read, build, edit, and test Simulink models by providing MCP tools and domain-specific skills based on Model-Based Design best practices.

A plugin for OpenCode that automatically reduces token usage by compressing stale conversation context into technical summaries and removing redundant tool calls.

A framework for building interactive UIs (charts, forms, dashboards) that render inline within AI chat clients using the Model Context Protocol.