Code Mode: give agents an entire API in 1,000 tokenskept by eddie • feb 23Cloudflare's Code Mode for Workers AI reduces MCP token usage by 99.9%, exposing the entire API via two search and execute tools.AboutCloudflare · Cloudflare Agents SDK · Model Context Protocol (MCP) · Cloudflare WAF · Cloudflare Workers · R2Filed#ai-agents#api#cloud-computing#developer-tools#open-sourceRelatedGitHub - cloudflare/agentic-inbox: A self-hosted email client with an AI agent, running entirely on Cloudflare WorkersCloudflare released Agentic Inbox, a self-hosted email client with an AI agent that runs entirely on Cloudflare Workers using Email Routing, Durable Objects, and R2.also on Cloudflare Agents SDK, Cloudflare Workers, Cloudflare, #cloud-computing, #ai-agents, #open-source, #developer-toolsIntroducing FastMCP 3.0 🚀FastMCP 3.0 introduces a composable architecture based on Components, Providers, and Transforms to build durable, production-ready MCP servers in Python.also on Model Context Protocol (MCP), #ai-agents, #open-source, #developer-toolsIntroducing Markdown for AgentsCloudflare introduces Markdown for Agents, automatically converting HTML to markdown for AI crawlers and agents to reduce token usage and improve structured data access.also on Cloudflare Workers, Cloudflare, #cloud-computing, #ai-agents, #developer-toolsCloudflare Workers and Hyperdrive with SvelteKit – Master.dev BlogIntegrating Cloudflare Workers and Hyperdrive with SvelteKit requires adjusting build scripts and using server hooks to provide per-request DB connections.also on Cloudflare Workers, #cloud-computing, #open-source, #developer-toolsHow OpenAI delivers low-latency voice AI at scaleOpenAI rebuilt its WebRTC stack with a relay-transceiver architecture to reduce latency and manage scale for real-time voice AI across 900 million users.also on Cloudflare, #api, #cloud-computing, #open-source
Code Mode: give agents an entire API in 1,000 tokens