AI models & inference

Video transcripts, summaries, chapters, study notes, and comparisons for AI agents.

Share context and questions between Claude instances — VS Code, claude.ai web, and mobile.

Persistent, outcome-grounded episodic memory for Claude. 14ms CPU retrieval, no GPU, no vector DB.

One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.

35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI

AI video generation via the Vivideo API: auto or manual mode, avatars, voices, brand kits.

Web data tools: Threads, Yelp, YouTube/TikTok transcripts, Google Trends, Airbnb, Jumia prices.

Show holiday photos from Vercel Blob inline in Claude chats.

AI-callable calculators and engineering models with real formulas. No hallucinated math.

Cloudflare Workers MCP server: ai-model-router

Cloudflare Workers MCP server: claude-skill-validator

Cloudflare Workers MCP server: llm-output-quality-monitor

Publish HTML from Claude or ChatGPT to a live URL with a QR code — no developer needed.

ElevenLabs in natural language: generate speech in any language, create and manage voices, compose m

Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only

Persistent memory for AI agents across Claude, ChatGPT and any MCP client.

PS metric horsepower to watts, number discarded

Short, finished fiction to discover by mood, genre or reading time inside ChatGPT.

Revit model query + APS Design Automation runner.

Speech-to-text for one immutable audio or video artifact, returning normalized text and timed segments for audio-to-text or video transcription workflows.

AI text-to-speech (ElevenLabs) — pay per call with USDC on Base

AI image editing API - edit images with USDC on Base

Audio AI tools: text-to-speech, voice cloning, music generation, stem separation, transcription.

Audio and video tools for your AI assistant: remove noise, enhance voices, transcribe, and more.

Provision private AI model endpoints on dedicated GPUs (Llama, Qwen, Mistral). Pay per minute.

AI model prices per provider, benchmarks, own AI behavior tests and AI economy data, with sources.

Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model.

Trainable non-fiction writing voice, presets, and an anti-AI-tells audit for Claude, via MCP.

Node-based AI design workflows on the Gemus canvas: generate images, video, 3D, and PPT.

Two independent AI models read a GPR, locate or pipe scan and flag the do-not-core call.