1774 Model Context Protocol servers — searchable, rated, ready to install.
Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.
Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.
Measured readings on open-source dependencies: health, end-of-life, model prices, incidents.
Check whether an LLM model id is deprecated, retiring, or retired, and what to migrate to.
Self-hosted MCP server exposing Claude Code as an agentic AI tool over streamable HTTP.
Model Context Protocol server for Google's Jules AI coding agent
Photo to technical drawing, CAD-ready DXF and DWG, 3D models and product renders.
AI poker arena for agents. Play rated poker on chipzen.ai against LLM bots and human-built bots.
Build and supervise fleets of agents from Claude Code, Codex or Cursor. Connects over OAuth.
Full-text search, browse, and resume across your coding agent sessions (Claude Code, Codex, Amp)
Session memory for coding agents: local-first recall, drift detection, on-device inference.
Source-checked CLI guides and model-aware planning for Claude Code, Codex, and Grok Build.
Connect Claude to your Gmail and Outlook inbox. Read, search, and manage emails via AI.
Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
A Model Context Protocol server for use with Tauri v2 applications
Self-hosted MCP server for time-series forecasting and tabular ML via foundation models.
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
Publish AI-generated web pages to a live, shareable URL from Cursor or Claude Code.
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
Sourced market and compliance research for Claude Desktop, Claude Code and Cursor.
Personal finance, bank account, and shared memory connector for Claude, ChatGPT, Gemini Spark & more
AI Linux & Windows server management with Claude MCP and fully private agents using local AI
MCP server for ML drift detection, MLflow registry diffing, and HMAC-gated model rollback
Clean messy CSVs: an LLM picks the steps, tested code does the work. Data untouched by the model.
POST /mcp