Browser-based 3D globe app that visualizes live public data—aircraft, ships, satellites, earthquakes, and cameras—with voice control.
AI-powered CLI code review tool that reads Git diffs or whole files, queries a configurable LLM agent, and returns line-precise comments.
A Claude Code plugin billed as an agent harness operating system, with an optional hosted GitHub App for private repositories.
A coding-assistant skill that forces ADHD-friendly replies: action-first answers, numbered steps, and no filler.
LLM-powered knowledge framework for enterprise document understanding, RAG Q&A, agent reasoning, and auto-built wiki knowledge bases.
Claude plugins and agent templates bundling finance skills, slash commands, and data connectors for banking, research, and fund ops.
MCP server and Claude Code plugin that keeps raw tool data out of agent context while indexing session history for compacted sessions.
Self-hosted control plane that orchestrates teams of AI agents with org charts, goals, budgets, and governance.
An agent skill that turns codebases or system descriptions into interactive, shareable HTML/SVG architecture maps.
An agent memory system that lets LLM agents learn over time by retaining, recalling, and reflecting on experiences, not just chat history.
Open-source framework that turns HTML, CSS, media, and seekable animations into deterministic MP4 videos via CLI or AI agents.
Terminal-based agentic coding tool that understands your codebase and handles tasks, code explanations, and git via natural language.
Self-hosted multi-user AI assistant platform with multi-agent workflows, web dashboard, CLI, IM channels, and a RAG knowledge base.
A hosted tool registry and proxy that lets agents call 3,000+ external API endpoints, plus shared team tools, with one base URL and token.
Kubernetes-based agent execution runtime that multiplexes many sandboxed agents onto shared workers with fast suspend/resume.
A runtime that sandboxes autonomous AI agents, enforcing kernel-level policies on file, syscall, and network access.
A plugin for AI coding agents that steers them to write minimal code via a ladder favoring reuse, stdlib, and native platform features.
Official Cursor plugins for developer tools, frameworks, and SaaS products, each packaged as a standalone directory with a manifest.
Open-source platform that gives AI agents usable computers via cloud desktops, desktop automation drivers, local VMs, and benchmarks.
A CLI that makes git worktree management easy, designed for running multiple AI coding agents in parallel.
A collection of Claude plugins that add role-specific skills, slash commands, and tool connectors for knowledge-work jobs.
Self-hosted service that pools free-tier LLM providers behind one OpenAI-compatible API with routing, failover, and per-key rate tracking.
Reverse engineering framework with disassembly, decompilation, graphing, and scripting tools for analyzing compiled code.