Architecture Deep Research: deep research for strategic system design decisions.

Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship.

Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps.

The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.

MCP Playbooks for AI agents

Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in one Rust binary. Give Claude, Cursor, and any MCP client a deep understanding of your codebase.

The implementation of Model Context Protocol (MCP) server for VictoriaMetrics

World-class creative director in a skill. Methodology-driven ideation (SIT, TRIZ, Lateral Thinking, bisociation) + a Cannes Lions evaluation engine, powered by a library of 571 legendary award-winning cases.

Connect your agent to the apps you already use - with or without Zapier.

Agent skills that fact-check the internet: claim-by-claim verification with sources and a 0-10 BS score for any YouTube video, article, tweet, or PDF

AI-driven quality & governance MCP Server for dbt projects. Audit coverage, profile data, detect schema drift, and auto-generate documentation — all through natural language with your AI assistant.

Apple HIG reference and cross-framework UI audit tooling for agents.

Production-Stage Visual Design & In-Codebase UI Engineering Suite

HAR: open agent harness (CLI + MCP) for coding agents. Isolated worktrees, deterministic verify, software factory workflows for Claude Code, Cursor, and Codex.

MCP server for YouTube — search videos, channels, playlists, and transcripts. Works with Claude, Cursor, Windsurf, and any MCP client.