Automates file management, document creation, and browser workflows on your desktop by running a local Electron agent; you bring API keys or run local models, control folder access, and save repeatable 'skills' for approved, auditable automation.
Provides a Claude Code plugin marketplace that supplies modular skills for security research, vulnerability detection, and audit workflows. Includes scanners, analysis skills, and developer tooling to embed LLM-assisted security checks into existing pipelines.
Connects AI assistants to Figma to extract design-system variables and components, create and edit frames, sync tokens bidirectionally to DTCG/CSS, and run WCAG scans. Read-only SSE, Cloud Mode, or NPX modes expose up to 106 tools.
Provides a modular collection of marketing “skills” (CRO, copywriting, SEO, analytics, growth engineering) expressed as markdown workflows so AI agents can apply marketing frameworks. Built to plug into Agent Skills–compatible agents like Claude Code and OpenAI Codex.
Grows a personal skill tree by crystallizing each solved task into reusable skills; a ~3K-line autonomous agent framework that gives an LLM system-level control of browser, terminal, filesystem, input/vision and mobile (ADB) via nine atomic tools, optimized for low token cost.
A production-ready performance and tooling system for AI agent harnesses (Claude Code, Codex, Cursor): reusable agents/skills, hooks, memory and security tooling, installer and CI integrations.
Rewrites text to remove common signs of AI-generated writing and produce more natural human prose while preserving source facts. Delivered as a portable agent skill (plain SKILL.md) that runs across agent harnesses, with voice-calibration and a strict no‑fabrication rule.
Pre-indexes a project's code into a local semantic knowledge graph that Claude Code can query—fewer tool calls and faster exploration with all data kept on-device. Features FTS5 search, call/impact analysis, auto-sync watcher, and multi-language support.
Browser-based, client-side video editor for multi-track editing, GPU-accelerated preview and local exports without uploading files; leverages WebCodecs/WebGPU and includes an AI upscaling option.
Desktop + CLI agent-native client for managing multi-session conversations, connecting to multiple LLM providers and external data sources, and creating shareable agent skills and automations without editing code.
Filters and compresses CLI command outputs before they reach an LLM, typically reducing token consumption by 60–90%. Single Rust binary with zero runtime dependencies, supports 100+ dev commands and integrates via a Bash hook into common AI coding tools.
Searches raw files with no vector DB or embedding step — drop documents in and query instantly, firing LLM calls only when a match needs reasoning. Adds Monte Carlo evidence sampling and self-evolving clusters as a low-overhead RAG alternative.