Cowork on a spatial canvas from the CLI — create canvases, generate images/text/video/agent responses, read results, recall past work, and manage nodes
Python toolkit, MCP server, and agent skills for reproducible, auditable clickstream and event log analytics. Helps AI agents, data scientists and analysts build, validate, and cross-check product analytics, quantitative UX, customer journeys, graph-based user flows, behavioral segmentation, A/B tests, process mining models, Markov chain simulation
A curated list of Hosted & Managed Model Context Protocol (MCP) Servers accessible via a simple URL endpoint.

Open-source Agent Operating System
Claude skill: refactor code to reduce cyclomatic complexity
MCP server that provides tools and resources to control and monitor robots using Nav2.
Kayforkind Content-Derived Design CLI. HTML in, standalone HTML out from the source's own nouns, dates, numbers, and colors. Not the reimagineit.ai interview SaaS.
The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 9 agents · 16 skills · 4 workflows. Fail-closed gates, test honesty, anti-anchored review.
MCP server for Things 3 with read/write support for tasks, projects, areas and tags.
SQL transactions learning tool (AI ready)
Privacy-conscious Apple Health export analyzer with bilingual health and multi-sport training reports
Astrid is a portable, capability-secure operating system for composable software.
Zero-configuration MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and standardized interface
Product-design, conversion & behavioral-science principles for SaaS
The meta-skill that builds and improves all your skills, including itself. Watches your work sessions (autonomous or human-led), captures patterns, corrections and judgement calls, and turns them into skill improvements and new skill candidates for your review. Practical application of the Augmented Expertise methodology. Open source: CC BY 4.0.
Record the talking head, Claude Code does the rest: the cut, the visuals, the voice, the sound effects, the thumbnail, and the YouTube upload. Every screen moment is built as Remotion TSX code, never screen-recorded.
A lightweight agent harness you bolt onto your app so an LLM can operate it — safely, and cheaply.
Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. 40 built-in policies, a local dashboard, no account required with a generous free cloud plan
Agent-driven research knowledge base. Agents collect, search, and synthesize web research into a persistent, searchable wiki.
A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.
Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread context, and cross-model review.
Simplified Gemini for Claude Code.
A MCP server allowing LLM agents to easily connect and retrieve data from any database
Agent Skill for generating AGENTS.md files following the agents.md convention | Claude Code compatible