3360 Model Context Protocol servers — searchable, rated, ready to install.
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
OpenRouter Models MCP.
Browser engine for AI agents. HTML in, Semantic Object Model out. 16x fewer tokens.
Post to 35+ social media platforms. Schedule & publish from Claude AI.
Model multiplexer — route tasks to Codex, Gemini, and Claude CLIs with smart routing.
Add OpenTelemetry tracing to Python AI agents. Supports LangGraph, LlamaIndex, CrewAI, OpenAI SDK.
Dividend-adjusted US equity total returns, risk decomposition, attribution & ETF hedge ratios
Cross-LLM persistent memory: store context once, recall it from any AI model.
Orchestrate multiple Claude Code agents in parallel from chat
Z-Image is an online interface for the Z-Image generation model with fast inference and prompt
MCP Server for SWOTPal — SWOT analysis tools for AI agents (Claude, Cursor, Windsurf)
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Extract structured insights from videos, podcasts, articles, and PDFs with multi-model AI
Detect fabrication and hallucination in any LLM output. 30+ models supported.
Pull Deep Memory from across your Claude Code Sessions — when you need it.
Mines your Claude Code and Cursor sessions into evidence-based CLAUDE.md / AGENTS.md rules.
Claude Code / MCP skills for the dev pipeline: discover, spec, design, build, ship, operate.
Multi-agent orchestration for Claude Code — consensus review, adaptive dispatch, skill learning
MCP server for AI-powered image recognition and description using OpenAI vision models.
Dynamically load Claude Code skills into AI agents without copying files.
Query GPT 5.2, Claude Opus 4.5, Gemini 3, Grok 4.1 simultaneously for AI perspectives
Generate 18 AI readiness files (llms.txt, ai.txt, RAG indexes, schema) for any website.
Real-time LLM output verification with 6-dim contract validation and auto-failover across providers.
AI model routing on your own vendor keys: pick the best model per prompt, or route and run it.
POST /mcp