buildwithclaude and agent-toolkit
The first tool provides a marketplace for Claude-related extensions, while the second offers resources for AI agents integrating with Sanity, suggesting they are complementary in the "vibe-coding-framework" category, as the former could host plugins and agents built using or for the latter.
About buildwithclaude
davepoon/buildwithclaude
A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw
Operates as a plugin marketplace accessible via Claude Code's `/plugin` command interface, indexing 20k+ community plugins, 4.5k+ MCP servers, and 1.1k+ external marketplaces alongside curated collections of agents, commands, and hooks. The platform uses a web UI and CLI-based discovery system with one-click installation, enabling users to install pre-configured AI specialists, automation commands, and event-driven hooks directly into Claude Code workflows. Supports programmatic contribution via markdown-formatted plugin definitions that define triggers, tools, and execution context for agents, commands, and hooks.
About agent-toolkit
sanity-io/agent-toolkit
Collection of resources to help AI agents build better with Sanity.
Provides an HTTP-based MCP server (`https://mcp.sanity.io`) exposing GROQ queries, document CRUD operations, schema deployment, and image generation tools directly to AI agents, plus curated agent skills covering Sanity best practices, content modeling, SEO/AEO, and experimentation. Integrates with Cursor, Claude Code, VS Code, Lovable, v0, Replit, and other MCP/Agent Skills-compatible platforms via OAuth authentication or CLI configuration.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work