Subagents are a good way for LLMs to to work on complex, multi-step tasks. Delegating to a subagent allows it to focus its context window on the subtask, thereby offloading the main agent's con...
agents-chat
Multi-user streaming AI chats built using RedwoodSDK RSCs, Cloudflare Agents, Vercel AI SDK, and OpenAI Agents SDK.
The Bitter Lesson of LLM Extensions
From ChatGPT Plugins to Agent Skills, a look at how we've been trying (and failing) to extend LLMs for the last three years.
Issue · BerriAI/litellm
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr...
Introducing the Fiberplane Playground for Cloudflare Agents
We're launching an Agents Playground for the Cloudflare Agents SDK
BerriAI/litellm
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
Build agents, not pipelines
There are only two ways to use LLMs in a computer program: as part of a pipeline, or as an agent. In other words, either you express the control flow of the program in code, or you give a LLM tools and allow it to manage the control flow itself1.
openai/openai-realtime-agents
This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.
freestylefly/wesight
Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.
Multi-user AI chat with RedwoodSDK RSC and Cloudflare agents
Multi-user AI chat with RedwoodSDK RSC and Cloudflare agents
truefoundry/trueforge
The open-source agent harness - the runtime layer that turns an LLM into a working agent.
Philipp Schmid on Twitter / X
Should we build the web for agents, not agents for the web? 🤔 A new paper argues that current research is misguidedly focuses on improving LLMs leading to significant problems with efficiency, reliability, and safety, proposing a new "Agentic Web Interface" (AWI) that sits on… pic.twitter.com/I90k6kdYdk— Philipp Schmid (@_philschmid) June 14, 2025
Adding payments to your LLM agentic workflows
This post discusses integrating the Stripe agent toolkit with large language models (LLMs) to enhance automation workflows, enabling financial services access, metered billing, and streamlined operations across agent frameworks.
Piecing together the Agent puzzle: MCP, authentication & authorization, and Durable Objects free tier
Cloudflare delivers the toolkit for AI agents with new Agents SDK support for MCP (Model Context Protocol) clients, authentication/authorization/hibernation for MCP servers, and Durable Objects free tier.
Pay from Agents SDK
Use withX402Client to pay for resources from a Cloudflare Agent.
Your agent needs a computer, not a container — introducing @cloudflare/computer
Agents need more than just a container to scale. We're introducing @cloudflare/computer, an agent runtime that dynamically orchestrates between fast, efficient isolates and full Linux containers to give every agent a computer of its own.
