3230 Model Context Protocol servers — searchable, rated, ready to install.
A browser your AI agent remembers. Learn a site once, replay it in one call, zero model calls.
Compacting proxy for OpenAI-compatible backends, with MCP tools to search the archived history.
Anthropic builds 14 of the Arena's top 50 models and OpenAI builds 5. But 44% of US adults use.
Long-term memory for Claude: Markdown in a git repo you own. Survives context compaction.
Persistent memory for AI agents: one brain shared across Claude, Cursor, Codex and more.
Lightweight self-hosted RAG knowledge base with hybrid retrieval and cited answers.
Set up the JEV model router for Claude Code, Codex and Cursor, and install MCP servers.
Search, read and grow a Karpathy-style LLM wiki of linked Markdown pages, with cited answers.
Daily AI signals for agents: today's 4 signals, what changed, ranked models and repos
Validate, plan, preview and run YAML data pipelines (ETL with LLM steps) and debug failed runs.
150+ image, video and audio models. Quote before you generate; pay as you go.
Is this AI/dev API down? Is this model deprecated, what replaces it? Live status for ~40 APIs.
New AI model, product and repo names as they surface, and the search terms behind them, sized.
Rotate API keys across AWS, GitLab, Cloudflare, OpenAI & more. Secrets never reach the model.
Your Apple Health data, food diary and lifts, for ChatGPT, Claude and Gemini. Approved on iPhone.
Track competitors' Meta ads, save swipe files and run Meta campaigns from Claude, ChatGPT or Cursor.
Self-hosted MCP task inbox shared by Claude Code, Codex, Gemini CLI and local LLMs.
SEO and GEO audit: check if a site can be read and cited by Google, ChatGPT, Perplexity and Claude.
qwen3.8-max trails claude-fable-5.1-max by 27 points. Over the past year the gap has stayed.
Count and cut tokens in prompts, chats and agents for any model. Runs locally, collects no data.
Check if your exit IP works for ChatGPT, Claude, Gemini: ASN, proxy/IDC type, risk, AI availability
Find why a scheduled AI agent (cron, launchd, systemd, Claude routine) stops silently. Read-only.
Main memory for Claude, ChatGPT or Codex: exact, dated notes of each project.
Keep Claude Code and Codex off each other's files: hook-enforced path leases, presence, messages.
POST /mcp