A teleoperation framework that allows users to control Unitree humanoid robots using XR headsets, featuring real-time first-person views and data recording for imitation learning.

An MCP server that gives AI agents free, keyless web search and anti-bot fetching capabilities, allowing them to bypass bot walls and crawl the web locally.

A distributed inference engine that clusters home devices over Ethernet to share RAM and accelerate LLM performance using tensor parallelism.

A ComfyUI custom node that accelerates MiniMax H3 model inference by up to 45% using a residual caching mechanism for DiT blocks.

An automated tool that downloads high-quality videos from multiple platforms and uses GPT to generate and burn in bilingual subtitles.

An A2C-based reinforcement learning agent that learns to optimize the capture of crackable WPA WiFi handshakes and key material from its environment.

An open-source enterprise data warehouse built in Rust that integrates analytics, vector search, and secure Python sandboxes for AI agent orchestration.

A private, cross-platform AI voice transcription and note-taking app that uses OpenAI Whisper to provide offline speech-to-text capabilities.

A high-performance, scalable LLM library written in JAX and Python for pre-training and post-training large models on Google Cloud TPUs and GPUs.

A lightweight CLI tool to manage and activate modular skills, expert agent roles, and slash commands for AI coding assistants like Claude Code and Cursor.

An inference engine for Hugging Face-compatible language and multimodal models that provides continuous batching, paged KV-cache management, and distributed serving.

A PyTorch-based library for time series forecasting that provides a high-level API and state-of-the-art deep learning architectures like Temporal Fusion Transformers and N-BEATS.

A comprehensive SEO audit tool that scans websites against 332 rules to provide actionable reports via CLI, desktop app, or AI agent skill.

一个本地离线的语音识别字幕生成工具，支持音频、视频和麦克风录音转SRT字幕，基于Qwen3-ASR和Whisper模型，可纯CPU或GPU加速，内置多种特化语言模型、说话人分离和卡拉OK逐字模式，并附带命令行接口和OpenAI兼容API。

An AI-powered tool that solves hCaptcha challenges using a mix of computer vision models and multimodal large language models.

A self-hosted AI workspace that integrates a coding agent with a web-based editor, terminal, and persistent state for a unified development environment.

A set of skills, agents, and diagnostic tools that give AI coding assistants deep expertise in Apple OS development to prevent bugs and accelerate debugging.

Client SDKs for the LangSmith platform, enabling developers to debug, evaluate, and monitor LLM applications and intelligent agents.

Codex Orchestration is a Codex plug‑in that lets you attach other LLMs (Claude Fable 5, Opus 5, OpenRouter models, etc.) to a task and assign them specific roles—Planner, Advisor, Designer, Executor. Codex stays the top‑level orchestrator, iterating plans, reviewing them, optionally designing UX artefacts, and finally executing code. The plug‑in is installed via the Codex marketplace, configured with skill prompts inside a Codex chat, and supports role‑specific effort levels. It aims to improve plan quality, enable parallel work, and reduce premium‑model usage. MIT‑licensed.

A context budget layer for AI coding agents that indexes repositories into symbol graphs to enable precise, tiered retrieval of code and metadata.

An interactive AI portfolio featuring a voice-enabled chatbot with agentic RAG, a 6-layer prompt injection defense, and a comprehensive LLMOps dashboard for monitoring and automated evaluations.

A toolkit for merging pre-trained language models in the weight space, allowing users to combine model strengths without additional training or high inference costs.

vLLM TPU is an open‑source plugin that lets you run PyTorch or JAX LLMs on Google TPUs using the same vLLM interface. It supports high‑performance features (async scheduling, KV‑cache offload, LoRA, speculative decoding, etc.) and is tested on many top models such as Gemma‑4, Llama‑3.1, and Qwen 3. Recommended TPUs are v7x, v5e, and v6e. The project provides quick‑start docs, a support matrix, and an active community for contributors.

An MCP memory layer for AI agents that provides persistent, structured storage and semantic retrieval of facts, tasks, and documents via a knowledge graph.

An MCP server that enables LLM agents to interact with the Lean theorem prover via LSP, providing tools for proof state analysis and theorem searching.

A network observability tool for Kubernetes that uses eBPF to index traffic and provides AI-driven troubleshooting via MCP integration.

An autonomous development loop for Claude Code that iteratively implements project requirements with built-in safeguards against infinite loops and API overuse.

Potpie creates a living context graph from your codebase and development tools, providing AI agents with the deep project knowledge required to plan, debug, and write code.

An autonomous business operating system for solo founders that provides AI agent skills to automate everything from idea validation and product building to marketing and 24/7 operations.

WebAI‑to‑API is a self‑hosted bridge that runs Google Gemini (via web API or a Playwright‑driven browser) and exposes it through OpenAI‑compatible endpoints, with a local dashboard and Docker support.

A generalized AI digital human video production workflow that transforms scripts and images into synchronized presenter videos with subtitles and effects.

A curated collection of pre-trained, state-of-the-art machine learning models in the ONNX format, enabling cross-framework compatibility and deployment.

A framework for building multi-agent AI applications that organizes agents into collaborative swarms based on real-world organizational structures.

An all-in-one model console WebUI that prioritizes Google Gemini's native capabilities while supporting OpenAI-compatible APIs, featuring a local-first architecture for privacy.

A code and markdown context engine that uses AST-aware structural search to provide AI agents with complete, meaningful code context without requiring indexing or embeddings.

A CCIE-level AI network engineering agent that automates monitoring, troubleshooting, and configuration across multivendor networks using hundreds of skills and MCP integrations.

An open-source framework for building AI-powered offensive and defensive security automation, used to establish the Cybersecurity AI research domain.

A secure, open-source terminal coding agent written in Rust that provides a sandboxed runtime and durable sessions for autonomous AI development.

LMMs‑Eval is an open‑source Python toolkit that unifies >100 multimodal benchmark tasks (image, video, audio) for evaluating large language models with vision/audio capabilities. It offers deterministic, statistically‑sound results, supports 30+ model families via vLLM, SGLang, or OpenAI‑compatible APIs, and includes a web UI, an HTTP evaluation server, and extensible model/task interfaces.

A lightweight version of SAM3 that uses knowledge distillation to compress vision and text encoders, reducing model size by up to 90% for efficient segmentation.

An AI agent system that automates the end-to-end mathematical modeling process, from problem analysis and model selection to code execution and academic report generation.

mcp2cli is a runtime CLI generator that turns MCP servers, OpenAPI specs, or GraphQL endpoints into instant command‑line tools. It supports OAuth, secret‑safe flags, baked configurations, usage‑aware ranking, and machine‑readable JSON output, enabling LLM agents and developers to call APIs with minimal token overhead.

A cognitive memory engine for AI agents that provides durable, temporal, and governed local-first storage to move beyond simple RAG.

The official OpenAI Go library that provides type-safe access to the OpenAI REST API for applications written in Go.

An MCP server that enables AI models to generate over 26 types of professional charts and diagrams using the AntV visualization library.

Humanize PPT is an open‑source Python orchestration tool that turns markdown into an audience‑state‑transfer (AST) slide plan, decides per‑slide media, hands off rendering to downstream HTML or PPTX skills, runs an automatic presentation‑check to flag “pretty‑but‑can’t‑talk” slides, and generates a lightweight presenter shell. It integrates with AI agents (Claude‑Code, Codex, Hermes) via a simple skill install, works with downstream renderers like `guizang-ppt-skill`, `frontend-slides`, `ppt‑master`, and media generators (`baoyu-image-gen`, Remotion). MIT‑licensed.

A Python library for differential inverse kinematics based on the MuJoCo physics engine, enabling robots to reach targets while avoiding collisions and respecting joint limits.

A Codex plugin that transforms reference images into animation-ready procedural Three.js objects by generating the necessary construction code through a structured analysis and review workflow.