A tool for adding revocable custom instructions to Claude Code, allowing users to preview changes before applying them to new AI conversations.

An AI-powered screenshot assistant that analyzes on-screen questions in real-time to provide answers while remaining invisible to screen-sharing software.

Firefox‑Reverse is a custom Firefox build that embeds an AI‑driven reverse‑engineering agent. The agent can automatically capture, trace, and reproduce encrypted request parameters (signatures, tokens, risk fingerprints) generated by obfuscated JavaScript, JSVMP, or WASM. It provides isolated fingerprint environments, 68 built‑in tools, model‑agnostic LLM support, and outputs ready‑to‑run Node.js/Python scripts (or pure‑JS code). Pre‑built installers are available for Windows, macOS, and Linux.

An evidence-grounded workspace for YouTube creators to research topics, generate AI-driven insights, write scripts, and create thumbnails using YouTube and Gemini APIs.

Code-as-World is a framework that represents the physical world as executable code to enable AI models to perform quantitative physical reasoning by discovering world representations through iterative simulation.

A vendor-neutral standard for packaging reusable AI agent skills and MCP servers into portable, distributable plugins.

An open-source, local-first desktop app that turns prompts into polished design prototypes and assets using any LLM provider you choose.

A coding agent tuned for small local models that uses a specialized scaffold to enable high-performance coding tasks on consumer hardware.

An autonomous research orchestration system that replaces the human-in-the-loop bottleneck with an AI-native engine for literature discovery, gap analysis, and hypothesis generation.

A desktop orchestration layer for AI agent teams that allows users to coordinate multiple autonomous agents from different providers to handle coding and project tasks via a Kanban board.

An AI-powered interview platform featuring resume analysis, RAG-based knowledge bases, and real-time voice/text mock interviews to assist candidates and recruiters.

A Python library that uses LLMs to extract structured, grounded information from unstructured text, featuring optimized processing for long documents and interactive visualization.

An MCP server that provides AI agents with a comprehensive suite of reverse-engineering tools for JavaScript, WASM, and native processes, featuring an adaptive tool-discovery system to manage token usage.

A high-quality voice conversion tool focused on simplicity and performance, providing a flexible platform for voice transformations.

A collection of 50 specialized Claude Code sub-agents that turn Claude into an offensive security research assistant for penetration testing and red teaming.

WorldX is an AI-powered simulation engine that generates a complete virtual world with autonomous agents, maps, and emergent narratives from a single text prompt.

Apache TVM is an open machine learning compilation framework that optimizes and deploys models into minimum deployable modules using a Python-first approach.

A collection of official AI agent skills that provide AI coding assistants with specialized knowledge for building, deploying, and debugging Expo and React Native applications.

A Rust-native persistent memory substrate for AI agents that enables local semantic retrieval, graph relationships, and adaptive learning across sessions.

TorchRL is a PyTorch‑native, modular reinforcement‑learning library that provides a unified TensorDict data model and interchangeable components (environments, collectors, replay buffers, loss modules, trainers, etc.) for building, scaling, and experimenting with RL, multi‑agent, model‑based, and LLM post‑training pipelines.

An MCP server that allows AI assistants to securely execute remote SSH commands and transfer files while keeping credentials isolated from the AI model.

A deterministic scanner and quality gate that detects and removes low-quality code patterns generated by AI coding agents across 10 programming languages.

A tool that turns public GitHub repositories into single synthetic prompts for AI coding assistants to recreate the project from scratch.

A 650M parameter OCR model for document intelligence that provides high-accuracy text recognition, layout analysis, and table extraction across 91 languages.

TE MAN is a ComfyUI plugin that adds an infinite‑canvas workflow, asset library, audio/video/image nodes, 3‑D director, batch prompt tools, and an AI‑assistant chat panel, enabling both local model inference and remote API usage for image, video, and multimodal generation.

A tool for AI agents to remove 64 AI-specific markers and clichés from Russian text, making it sound more human and less detectable.

A collection of domain-specific skills for Claude Code that provide deep expertise in copywriting, frontend design, SEO, and video production via slash commands.

A prompt-directing workflow for AI agents that generates structured production plans and prompts for creating character-consistent outfit-change videos.

An AI coding factory that automates the process from ticket intake to reviewed pull request, featuring adversarial review and tamper guards to ensure code quality.

An open-source macOS text utility that provides a contextual popup bar with AI, text transformation, and custom script extensions when text is selected.

An open-source PDF translation tool that preserves the original layout and formulas, specifically optimized for scanned and image-based PDFs.

An agent communication SDK that provides a unified interface for AI agents to interact with humans across multiple channels like Slack, Discord, and Telegram using a single handler.

An open-source platform for running AI agents as a team, providing secure sandboxing, centralized credential injection, and identity provider integration.

An open-source credential proxy and vault that prevents AI agents from leaking secrets by brokering API access through a secure MITM proxy.

An open-source robot simulator providing a complete development environment to model, program, and simulate robots, vehicles, and mechanical systems.

A curated, CC‑BY‑4.0 collection of 6 243 ready‑to‑use prompts for ByteDance’s Seedance 2.0 video‑generation model, with a web gallery, featured examples, and contribution guidelines.

An AI-powered tool that generates complete multi-page social media posts, including outlines, copywriting, and visually consistent images, from a single sentence.

A type-safe, provider-agnostic TypeScript SDK for building streaming chat, tool-calling agents, and multimodal AI applications across various JS frameworks.

A system to run, manage, and scale AI workloads across any cloud provider, Kubernetes, or Slurm cluster using a unified interface.

A voice-controlled interface for Claude Code that allows users to brainstorm designs, drive automated builds, and monitor multiple AI coding sessions via voice.

A free, open-source AI video generator that uses cloud APIs to create narrated, auto-subtitled multi-scene videos from text or images without requiring a high-end GPU.

A Docker‑based deployment kit for serving the 27‑billion‑parameter Qwen 3.8 model on NVIDIA DGX Spark using SGLang. Includes ready‑made scripts for three speculative decoding engines (EAGLE/MTP, DSpark, DFlash2), benchmark utilities, and easy configuration of context length (up to 1 M tokens), concurrency (up to 10), and quantisation. Designed for engineers who need high‑performance LLM inference on a‑arch64 GPU server.

A deployment tool for Grok Build that safely manages the installation, verification, and removal of global custom instructions (home rules).

WorldClaw is an agentic 3D generation framework designed to create large-scale, open-world 3D environments.

A comprehensive collection of code and resources for optimizing AI systems, focusing on GPU tuning, distributed training, and high-throughput inference scaling.

An evaluation and evolution tool for AI Agent Skills that uses declarative YAML cases and an automated loop to measure, repair, and improve agent capabilities.

memsearch is a Python library and CLI that records AI coding‑assistant chats as Markdown, builds a hybrid (BM25 + dense) Milvus index, and provides cross‑platform recall via plugins for Claude Code, Codex, DeepSeek Harness, OpenClaw, and OpenCode. It supports local ONNX embeddings, optional Zilliz Cloud backend, background project/user notes, and automatic skill distillation.

A hardware detection and recommendation tool that tells users which open-weight AI models will run best on their specific machine based on their CPU, RAM, and GPU.