3818 Model Context Protocol servers — searchable, rated, ready to install.
Generate images (Nano Banana), video (Veo, Gemini Omni), speech and music (Lyria) with Google models
One memory for AI agents in Claude Code, Cursor, Codex and ChatGPT that flags conflicting facts.
Let Claude use your Zen Browser, like Claude in Chrome. No extension, only sites you allow.
14 labs launched 50 named AI models from 6 Jul 2026 to 27 Sept 2026. Alibaba's Qwen team led.
Qwen3.8-Max rates within 30 Arena points of Claude Opus 5.5 for 3.3× less per output token..
Scans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats
UN Charter (1945, as amended) as an executable model with worked cases; not UN-affiliated
Takes the people out of text before a model sees it, and puts them back in the reply.
Agent research API for 15 disease areas, plus a T1D cure lab, sourced evidence ledger and models.
Local ledger of Claude Code and Codex tokens, API-equivalent cost, limits and token-rate changes.
Records the prompt, model and files an agent declared for a line. It does not prove who typed it.
Run Apple Search Ads from Claude: performance, recommendations, keywords, budgets, launches.
Message boards for AI agents: Claude, ChatGPT, Grok Bot, Muse and Codex post and read each other.
Safe folder access for ChatGPT and Claude: read, write and search files, risky tools opt-in.
Fail-closed privacy layer that pseudonymises enterprise API data for LLM agents and MCP clients.
CODATA CDIF descriptions of published Semantic Data Charter models; read-only, no account.
Review declared AI data permissions, expiry and regions; model revenue splits without moving funds.
Anthropic has 7 of the top 10 creative writing models and Google 3. Meta's muse-spark-1.2.
Tuval Studio MCP: Graphic design, AI design & PDF catalog generator for Claude, Cursor & AI agents.
Shared AI memory. ChatGPT, Claude, Cursor and any MCP app read and write the same memory.
CompanyGraph: Written once, read by both
LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.
OpenAI's models hold 17.9% of all 12.3M Arena votes and none of the top 20 seats. Anthropic's.
Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
POST /mcp