Cloudflare compounds as the developer platform for the AI era: revenue keeps growing fast, developers keep adopting Workers, and it keeps shipping AI platform launches.
8 rated major in the last 90 days; newest "Agents - New persistent browser tool in the Agents SDK, with tabs and logins that last between turns", 6 days ago.
Kill condition
No major launch in 90 days
Signal
Each Workers AI or Agents changelog entry, rated a major launch or minor
Verdicts, newest first
Cloudflareminor
The entry adds a single model, PhoneLLM Mini, to the existing Workers AI catalog, which the rubric rates minor.
Title
Workers AI, Realtime - Pipecat PhoneLLM Mini now available on Workers AI
@cf/daily-co/phonellm-mini-alpha-2 , a model from the Pipecat ↗︎ team at Daily, is now available on Workers AI . PhoneLLM is built for voice agents and other realtime AI applications, where a model has to reply quickly and call the right tool mid-conversation. In a voice agent, the language model sits between speech-to-text and text-to-speech, so every second it takes adds to the caller's wait. De
The Cloudflare Agents SDK now provides a browserTool that gives your agent a Browser Run browser it can return to on later turns. Your agent can open a website, inspect a page, and come back to it with its tabs, cookies, and login session intact while the browser session remains alive. When you give browserTool to your agent, the model writes code that drives the browser through the Chrome DevTool
The entry extends the existing Cloudflare API MCP server to send Workers Issues as MCP Events; it is an added option on an existing product, not a new product, model family or major API version.
Title
Agents, Workers - Cloudflare API MCP server sends Workers Issues as MCP Events
Workers Issues provides built-in error monitoring for Cloudflare Workers. It detects production failures and groups related failures into issues without an SDK or application wrapper. The Cloudflare API MCP server now sends these issues as MCP Events ↗︎ , the first event it exposes. MCP clients discover cloudflare.alert.workers_observability_real_time_issue with events/list and subscribe with even
The Cloudflare Agents SDK now provides a web_search tool that searches the public web through the Cloudflare Web Search API , powered by ceramic.ai, Exa, and Linkup . When you give the web_search tool to your agent, the model provides a query and max results, and receives back a short numbered list of titles, URLs, and trimmed descriptions. When you also provide the web_fetch tool to your agent, t
The Agents SDK now supports OpenCode 2.0 ↗︎ through the experimental OpenCodeHarness . Run OpenCode inside a plain Durable Object, with sessions stored in SQLite and Lifecycle jobs that wake interrupted work after eviction. The agents/models/opencode provider connects OpenCode to Workers AI through the AI binding. OpenCode plugins extend the harness with custom tools, remote MCP servers, and skill
The Cloudflare Agents SDK now provides a web_fetch tool that reads webpages, PDFs, and supported Office documents, using Workers AI Markdown Conversion to turn them into text the model can read. The tool requests Markdown directly from sites that support Markdown for Agents and formats JSON for the model. When you give the web_fetch tool to your agent, the model provides a URL and receives back th
The entry adds Cloudflare skills to the existing Cloudflare API MCP server through an extension; it is not a new product, model family or major version, and the entry does not say it is generally available.
Title
Agents - Cloudflare API MCP server serves Cloudflare skills
The Cloudflare API MCP server now serves Cloudflare skills ↗︎ through the Skills over MCP extension ↗︎ . MCP clients that support the extension discover the skills with skills/list and read their files at skill:// / . To use them, add https://mcp.cloudflare.com/mcp to an MCP client that supports the extension ↗︎ .
Clef-omni joins the existing Clef family on Workers AI alongside a Clef-flash price cut, which is a single model added to an existing catalog plus a price change.
Title
Workers AI - Clef-omni adds audio and video input, Clef-flash is now cheaper, and Clef is faster
@cf/cloudflare/clef-omni is now available on Workers AI. Clef-omni is a decision model that takes audio (WAV or MP3) and video (MP4 or WebM) input alongside text and images. It joins Clef and Clef-flash in the Clef family of open-weight decision models. We also cut the price of Clef-flash, so it now costs less than Jev, and made Clef faster. Clef-omni: one decision model for every modality Previou
The entry announces first-class Agents SDK support for building agents on the Pi harness via a new PiHarness class, a new capability that is available now.
Title
Agents, Workers - Run the Pi Durable harness on Cloudflare with the Agents SDK
The Agents SDK now provides first-class support for building agents using the Pi harness. You can build long-running agents using the combination of Pi 1.0 ↗︎ , Pi Durable ↗︎ , and the new PiHarness class that the Cloudflare Agents SDK provides, ensuring your agent's work is durably persisted, even if interrupted mid-turn. Built with Earendil ↗︎ , this integration is our first step toward first-cl
The entry says the Workers OAuth Provider is now v1 with a new split API, a new major version of an SDK.
Title
Agents, Workers - The best way to do MCP auth just got better: Workers OAuth Provider goes v1, with a new split API and full support for MCP 2026-07-28
@cloudflare/workers-oauth-provider ↗︎ is now v1, with a new split API. One Worker acts as the authorization server: it signs users in and issues tokens. Your MCP server acts as the resource server, and can run in another Worker. It validates each token with the authorization server over a Service Binding , without crossing the public Internet. It supports the MCP 2026-07-28 authorization specifica
Meet @cf/cloudflare/clef and @cf/cloudflare/clef-flash , the first models trained by the Cloudflare Workers AI team, available on Workers AI today. Clef is a decision model, in the same family as Typesafe's Jev ↗︎ . Instead of generating text, it reads an input state and a set of typed questions, then returns a probability for every allowed answer. Your agent gets a structured decision it can act
The rejectIfBusy option lets synchronous Workers AI inference requests fail when capacity is unavailable. Use it when your application should not wait in a capacity queue. Pass the option as the third argument to the Workers AI binding: const response = await env. AI . run ( "@cf/google/gemma-4-26b-a4b-it" , { messages: [{ role: "user" , content: "Explain capacity queues." }], }, { rejectIfBusy: t
@cloudflare/voice v0.4.0 now lets you inspect where each Voice Agent turn spends time and how it ends. client. addEventListener ( "turnmetrics" , ( turn ) => { console. log (turn.outcome, turn.turnTotalMs); }); About the Voice package The @cloudflare/voice package lets you build real-time voice agents with Cloudflare Agents. It streams microphone audio to an Agent over WebSocket, transcribes speec
@cf/zai-org/glm-5.3 is now available on Workers AI. It is Z.ai's flagship agentic coding model, built for long-running, tool-driven development workflows rather than single-turn chat. GLM-5.3 uses the same base model as GLM-5.2, with every gain coming from post-training. The results are substantial on coding and agentic benchmarks: Z.ai reports ↗︎ a 50% improvement over GLM-5.2 on its in-house Z.a
@cf/zai-org/glm-5.3-flash is now available on Workers AI. It is the first natively multimodal model in the GLM-5 series, built on a Mixture-of-Experts architecture with 320B total parameters and 18B active per token. GLM-5.3 Flash is the first GLM-family model on Workers AI to support multimodal inputs. It outperforms GLM-5.2 across benchmarks and real-world workloads at a lower price, while appro
Wrangler and the Cloudflare API MCP server now use optional OAuth scopes. During authorization, you can choose which optional scopes to grant instead of approving every scope requested by each client. The consent dialog now includes the option to edit the permissions you grant to Wrangler or the Cloudflare API MCP server: You can then choose which specific permissions to grant: Required scopes rem
@cf/qwen/qwen3.8-27b is now available on Workers AI. Qwen 3.8 27B is a 27-billion-parameter instruction-tuned vision language model from Alibaba's Qwen family. It processes images and text together, with reasoning and function calling for agentic workflows. Key capabilities: Vision : Accept image and text inputs and generate text responses. Reasoning : Support thinking mode for complex, step-by-st
@cf/deepseek-ai/deepseek-v4-pro-0813 and @cf/deepseek-ai/deepseek-v4-flash-0731 are now available on Workers AI. DeepSeek V4 Flash and DeepSeek V4 Pro are the first Workers AI models with a full one million (1,048,576) token context window . Use them for long-horizon agentic workflows, large codebases, and multi-step reasoning that exceed the context limits of every other model hosted on the platf
Workers AI and AI Gateway now provide a unified path for accessing models and managing inference traffic. Use the same AI binding and REST API to call models hosted on Workers AI or by supported third-party providers, with AI Gateway providing observability, logging, caching, security, and billing controls. Unified entrypoints and observability The AI binding supports both Workers AI and third-par
Agent tracing is now available for applications built with the Agents SDK. Traces show each agent turn alongside model calls, tool runs, approvals, token usage, and Workers runtime operations. Turn on Workers tracing in your Wrangler configuration: { "$schema" : "./node_modules/wrangler/config-schema.json" , "observability" : { "traces" : { "enabled" : true } } } [ observability . traces ] enabled
We're releasing an early preview of @cloudflare/computer ↗︎ , an open-source agent runtime that gives every agent its own computer. The runtime dynamically orchestrates between fast, efficient isolates and full Linux containers, so the agent always runs on the right compute primitive for the task at hand. @cloudflare/computer provides a virtual filesystem backed by SQLite, which you can populate f
We are limiting Workers Free plan access to a few resource-intensive models so we can prioritize capacity for the broader Workers AI user base. This helps everyone get a more reliable inference experience, with fewer 429 and 3040 (Out of Capacity) errors. The following models now require the Workers Paid plan : @cf/moonshotai/kimi-k2.6 @cf/moonshotai/kimi-k2.7-code @cf/zai-org/glm-5.2 On the Worke
Cloudflare's product-specific MCP servers now support the new MCP 2026-07-28 Specification. Each request runs on a fresh stateless server without an MCP protocol session or protocol-specific Durable Object. The /mcp endpoint also accepts stateless requests from 2025 Streamable HTTP clients. Most clients can reconnect without configuration changes. Use /mcp for new connections. Historical /sse URLs
Agents SDK v0.20.0 adds client and server support for the MCP 2026-07-28 release candidate ↗︎ . Workers can serve tools, prompts, resources, and elicitation without an MCP transport session or Durable Object. Agents can connect to both MCP 2026-07-28 servers and existing legacy servers. Client support The MCP client manager now uses @modelcontextprotocol/client . For each connection, it probes for
The agents , @cloudflare/ai-chat , @cloudflare/codemode , and @cloudflare/think packages now support AI SDK v6 and v7. Existing applications can remain on v6 when updating these packages. Applications can also adopt v7 without changing the Cloudflare Agents APIs they use. The supported peer ranges are ai@^6 || ^7 and @ai-sdk/react@^3 || ^4 . Use matching major versions: pair AI SDK v6 with @ai-sdk
This release reduces repeated MCP schema conversion and adds an opt-out for Think's automatic MCP tool exposure. It also lets non-AI-SDK hosts invoke the durable Code Mode runtime directly. Control direct MCP tool exposure in Think Agents SDK MCP clients now reuse converted input and output schemas while a live connection keeps the same tool catalog. This avoids converting every MCP JSON Schema to
Agents connected to Model Context Protocol (MCP) servers with addMcpServer can now handle elicitation ↗︎ requests. Elicitation lets an MCP server request user input while it handles a tool call. Form mode collects structured, non-sensitive data. URL mode asks for consent before opening an out-of-band flow, such as third-party authorization or payment. sequenceDiagram participant User participant A
A research journal, not investment advice. Statuses are computed from the terminal’s own stored data against kill conditions written before the data arrived; OpenRouter is one aggregator’s traffic, not market share. Judged claims stay unresolved until the judge rates them.
Not investment advice.
A claim you would like tested needs a public number behind it. Request a dataset on GitHub.