A Node.js rendering and validation system that enables AI agents to turn codebases or system descriptions into interactive, validated system maps.

A set of rules and plugins for AI coding agents that prevents over-engineering by forcing them to follow a hierarchy of simplicity before writing new code.

A browser-based design tool for sketching Material 3 Expressive screens and converting them into natural-language prompts for AI coding tools.

An agent harness operating system that provides a coordinated engineering system and toolbox for AI agents to plan, test, and verify code changes.

A collection of 163 standardized skills for AI agents to perform complex scientific research workflows across biology, chemistry, medicine, and physics.

An AI orchestrator that lets developers run multiple CLI-based coding agents in parallel isolated worktrees to compare results and accelerate development.

A cybersecurity skills router that provides AI agents with structured methodologies and tool-routing rules for reverse engineering, pentesting, and CTF tasks.

A local-first search layer that unifies ripgrep, BM25, and vector search to help humans and AI agents efficiently retrieve evidence from local workspaces.

A lightweight, stealthy headless browser engine written in Rust for AI agents and web scraping, serving as a high-performance replacement for headless Chrome.

An open-source container and VM runtime for macOS written in Rust that provides a drop-in Docker replacement and isolated microVM sandboxes for AI agents.

A high-performance serving framework for LLMs and multimodal models that provides low-latency, high-throughput inference across single GPUs and large distributed clusters.

A data visualization skill for AI agents that generates professional, editorial-style charts and HTML reports using a unified visual grammar.

OmniRoute is an open‑source, self‑hosted router that aggregates hundreds of LLM providers (including 90+ free tiers) behind a single OpenAI‑compatible endpoint. It auto‑selects the best backend, falls back on failures, compresses prompts to save tokens, and shows live free‑tier usage. Install with `npm i -g omniroute`, run locally, and call the `auto` model to get free, resilient AI responses without managing multiple keys.

An autonomous research system that turns runnable, measurable projects into continuous, evidence-driven research runs to find optimal solutions through parallel agent exploration.

A fast Rust-based library for PDF classification and text extraction that converts PDFs to structured Markdown and selectively applies OCR only when necessary.

A management tool for installing and managing DLSS 5 Neural Rendering across various games and emulators, supporting both native DLSS and non-DLSS titles.

An API for searching, scraping, and interacting with the web at scale, converting website content into clean Markdown or structured data for AI agents.

A tool that maps codebases, docs, and media into a knowledge graph, allowing developers to query relationships and trace paths between concepts instead of grepping files.

A source control system for coding agents that links Git commits to the agent sessions and reasoning that produced them, providing shared memory across different AI agents.

A token-reduction toolkit for AI agents that shrinks both input and output tokens through a local proxy, a terseness-enforcing skill, and image-based prompt compression.

An open-source inference server that profiles local hardware to recommend, tune, and run the best AI models for agent workloads.

A persistent background runtime for coding agents that ensures sessions remain active across restarts and network drops while providing a socket API for agent coordination.

An independent auditing framework for AI agents that evaluates operational assurance and business KPIs through a graded scorecard of security, reliability, and compliance inspections.

A CLI tool that simplifies LLM fine-tuning and post-training, featuring layer streaming to enable training 8B models on GPUs with as little as 4 GB of VRAM.

A unified OpenAI-compatible API gateway that aggregates free tiers from dozens of LLM providers into a single endpoint with smart routing and failover.

An open-source web crawler and scraper that converts websites into clean, LLM-ready Markdown for RAG, AI agents, and data pipelines.

A design guidance system for AI coding agents that uses a shared command vocabulary and 61 deterministic rules to prevent generic AI-generated frontend designs.

An edge-native MoE serving engine that enables running 290B+ parameter frontier models on consumer gaming PCs and laptops using bandwidth-adaptive execution and elastic memory management.

A task generator that creates new, distribution-matched ARC-AGI-1 style tasks to evaluate AI models on unseen problems and prevent benchmark contamination.

An open-source proxy that lets you run popular coding agents using 50+ free, paid, or local LLM providers with automatic failover and token optimization.

A local AI server stack that provides a one-command installation of inference, chat, RAG, and agent tools for private AI on your own hardware.

A library of production-grade engineering skills and workflows for AI coding agents to ensure they follow senior-level best practices in software development.

A local-first tool that tracks AI coding token usage and costs across 41 tools and agents, helping developers find waste and optimize their spend.

A proxy server that provides OpenAI, Gemini, Claude, and Grok compatible API interfaces for CLI tools, allowing access via OAuth or API keys.

A service and agent skill set to strip AI provenance marks and watermarks from text and various file formats for privacy and hygiene.

A tool that integrates multiple AI agent harnesses like Claude Code and Pi into the Codex Desktop interface, enabling unified control and cross-agent collaboration.

An open-source toolkit that implements a spec-driven development process for AI coding agents, ensuring high-quality software by requiring structured specifications and planning before implementation.

An autonomous AI penetration testing tool that uses multi-agent orchestration to find, validate with PoCs, and fix security vulnerabilities in applications.

A security scanner for AI agent skills that detects vulnerabilities and malicious patterns using static analysis and LLM-based semantic evaluation.

An adaptive web scraping framework that bypasses anti-bot systems and automatically relocates data elements when website designs change.

An automated App Store screenshot and preview video generator for iOS apps that can be driven by coding agents or used manually via CLI.

An open-source context database for AI agents that organizes memories, resources, and skills as a virtual filesystem to enable deterministic and token-efficient retrieval.

A tool that enables NVIDIA DLSS 5 Neural Rendering on AMD Radeon RX 9000 and 7000 series GPUs for DirectX 12 games using FSR.

A lightweight Python utility that converts various file formats (PDF, Office docs, images, audio) into Markdown to make them easily consumable by LLMs and text analysis pipelines.

A semantic code intelligence platform that provides AI agents with a pre-built knowledge graph of a codebase to eliminate slow file-by-file discovery and reduce token costs.

A software factory framework that turns AI coding agents into a virtual engineering team with specialized roles for planning, review, and QA.

A fast Rust library that converts various office documents (Word, PowerPoint, Excel, PDF, etc.) into clean, LLM-ready GitHub-Flavored Markdown.

A guardrail system for AI coding agents that prevents over-engineering and task creep by enforcing explicit task boundaries and intercepting unauthorized actions.