Productivity

A package manager for agent skills — manage, install, and link skills across your projects.

Your AI agent skills, finally organized. A macOS app to browse, edit, and manage skills across Claude Code, Cursor, Codex, Windsurf, and Amp.

A skill for AI agents to manage home pantry inventory, shopping lists, and purchase history.

Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.

The Runtime Where AI Agents Build, Ship, and Evolve — a modular, cross-platform, AI-powered productivity platform with federated app collaboration and extensible agent workflows.

Salesforce MCP Library — local stdio bridge for Salesforce MCP endpoints using OAuth client credentials, featuring a reusable Apex MCP library and JSON-RPC 2.0 core.

Universal MCP gateway for AI agents — 422 tools, 127 providers. GitHub, flights, stocks, news, search, maps, and web scraping. Pay-per-call with x402 USDC.

Universal AI Memory Platform — Remote MCP Server + Web Management UI. Give AI assistants persistent memory across conversations.

MCP server aggregating free tiers, startup credits & developer tool deals — 4 tools, 54 categories, 1,525+ offers for AI agents.

Dropshipping automation with AI — import AliExpress/Alibaba products to Shopify & Wix via DSers. Open-source MCP server with bulk import, pricing rules, and multi-store push.

Production-tested commands, skills, and workflow patterns for Claude Code. Developed through 6+ months of daily use. Includes explore→plan→next→ship workflow, session handoffs, MCP integrations, and domain skills. Copy what works, adapt to your needs.

Bridge Claude Code / Codex to IM platforms — chat with AI coding agents from Telegram, Discord, or Feishu/Lark.

Claude Code skills & config for multi-agent research workflows

Shareable Claude Code infrastructure for PhD researchers — skills, agents, hooks, and rules for academic workflows

Research notebook on Claude Code architecture: plugin system, multi-agent orchestration, skill composition, and workflow patterns. Public analysis of official interfaces.

AI-powered development tools. 21 agents, 22 commands, 29 skills, 1 hook, 1 MCP server for code review, research, design, and workflow automation.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for qwen code, cursor and kilo code.

Hierarchical agent skills for domain ontology planning, research, construction, and validation with saved research artifacts and eval-ready workflows.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Personal Agent Control Plane for Claude Code — session memory, skill routing, research ingestion

An open-source agentic AI system for real-time and scheduled research on user-defined topics with custom skills. Uses local models, web search, and Python to generate multi-format reports, chat with results, and deliver them to Discord.

An agentic skills framework and structured software development methodology for Claude Code. Enforces research, specification, planning, testing, and implementation workflows.