Over the past 6 months, we've rearchitected Cline's agentic... loop into a standalone "cline core" gRPC service that runs independently of any editor. This enabled us to decouple from VS code and build - JetBrains (released in GA this week) - CLI built in Go (releasing soon) - Secret project that may be announced soon The CLI is our newest product and will ship without a TUI. Our focus is to release a true primitive. something close to the metal that pipes cleanly into RL environments, CI/CD systems, scripts, and automation workflows. Any "presentation layer" mentioned above can connect to the same running cline core - maintaining full feature parity (e.g. checkpoints, settings, api configurations), context, and conversation state. There's an SQLite-based instance and file/directory lock registry that prevents port conflicts and coordinates graceful shutdowns between paired processes - so you can start up thousands of cline instances in parallel with no conflicts or dangling processes. What's remarkable is that this cline core architecture opens Cline to any interface imaginable: mobile apps, web dashboards, custom tools - all powered by the same intelligent core that understands your codebase.show more

🚨 This tool just made every AI coding plugin... look outdated. Cline CLI 2.0 is a completely rebuilt, open-source AI coding agent that runs entirely in the terminal. Model-agnostic, editor-agnostic, Apache 2.0 licensed, and trusted by over 5 million developers. Same core engine as the VS Code extension rebuilt for how serious development actually happens. The new interactive UI feels genuinely native. Redesigned navigation, real-time agent reasoning, model switching mid-session, all without leaving the terminal. Parallel agents let multiple Cline instances run across tmux panes simultaneously, each with fully isolated state, working different tasks on different branches without conflicts. Headless mode with the `-y` flag plugs Cline directly into CI/CD pipelines, pipe a git diff in, get a code review out. And the `--acp` flag connects to Zed, Neovim, Emacs, and any ACP-compatible editor, so there's no forced editor choice. At launch, Minimax M2.5 and Kimi K2.5 are completely free. No API key. No credit card. Zero barrier to try it. `npm install -g cline` Docs → GitHub → The future of AI coding isn't a plugin. It's infrastructure.show more

New course: MCP: Build Rich-Context AI Apps with Anthropic.... Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!show more

Reviewing AI-generated code is the new bottleneck. Writing code... was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.show more

Right now the main paradigm that we think of... agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.show more

AOC in Berlin: "We all need to buckle up.... That is the moment that we are in. But if there is any place that shows that good people can prevail over the horrors of inhumanity, it is Berlin. It is Berlin. And it is so many other places around the world that can be a front line to show that we can overcome and we can defeat fascism by a class based solidarity that champions all of us. I think about this, I think about this, and I'll end with this note, but I think about this very often because, of course, the universal health care systems in Europe are the envy of every American. And it is truly, ah, such a revolutionary. Environment that you all grow up in the universality of health care, because it really is a decision and an affirmative material commitment to everyone's basic humanity, to human dignity. And to me, it is not a coincidence that universal health care systems across Europe were established in the wake after World War Two. They are directly connected where you had all of this destruction, in all of this rubble that was built on a politics of persecution and division. But when we decided to move past that, we built material systems based on universality, affirming our our human dignity. And I think it's so important for us to recall those lessons for today, ah, as we confront many of the shadows of those similar movements."show more

GPT-5 is live in Cline. We've been working with... OpenAI to get this model ready, and here's our take: it's disciplined, persistent, & highly competent. It's collaborative in planning & and a diligent operator while acting. It plans thoroughly, asks optioned follow-ups when needed, & then gets out of the way and ships code. On long tasks it keeps going before pausing to check in. It follows instructions to the letter. And most importantly -- it writes good code. GPT-5 is like "The Wolf" from Pulp Fiction. Comes in, assesses the situation, then executes. Here's what you can expect from GPT-5 in Cline: > verbose while planning; terse while executing > asks a lot of good clarification questions, & frequently provides options when appropriate > strong context retention and persistence over long horizons (256k context window) > good at diff-style edits and multi-file changes (we'll monitor as more usage data comes in) > quiet in Act mode -- writes code without yapping Metaprompting is another strength. We tested early with OpenAI and used GPT-5 to tune our own prompt for GPT-5. Here's a pattern we like: “Answer from your own perspective: what changes or additions would help you better follow this prompt? Here is the prompt (or snippet): [snippet]. Users have complained about X and Y. What minimal edits would you make while keeping the rest intact?” Do you need to change any of your existing patterns in Cline? No -- it's good out of the box. Give a clear goal and constraints, let it plan, then let it cook. Expect more clarifying questions than most models. Pricing: $1.25/M input tokens (+90% cache), $10/M output. Roughly half of Sonnet 4 ($3/$15). Want to try GPT-5? Use it in Cline today for pure, unfiltered inference via the OpenAI, Cline, or OpenRouter providers. (fyi -- GPT-5 one-shotted this browser DAW below on the prompt "build something impressive to show me what you're capable of")show more

Why did so many languages copy async/await from C#?... Anders Hejlsberg(Anders Hejlsberg) - creator of TypeScript, C# & Turbo Pascal - on what they got right with the design: #1 - async/await was designed to solve a common problem in the event-loop model: "A lot of languages are built around cooperative multitasking in the sense that they have an event loop that sits and dispatches events. Then you handle the event and then you yield back to the event handler loop. And it all runs in a single thread cooperatively. The problem with that is if you then want to do some long running work: how do I stop in the middle of this piece of long running work and yield back to the event loop cooperatively? And then when my result is ready, I can come back and continue executing here." #2 - state machines are the solution, but hard to build: "Well, in order to do that in an inverted architecture like that, you have to build a state machine. State machines are notoriously hard for people to implement because you've got to move all of your state off of the stack into objects. And then you have this big case statement that envelopes your entire logic. It's a nightmare to figure out. But, the transformation from serially executing code into a state machine, its continuation-passing-style translation is actually one that you can do in a machine-based fashion." #3 - compilers are good at writing state machines: "You can have the compiler write the state machine if you introduce syntax that allows you to indicate where you want to yield. And that's what await is. Await is basically saying, I want to yield here, and I want to yield this promise, and then when the promise completes, I want you to come back here and continue executing. Then the compiler writes a state machine around it and it actually turns it into this big switch statement and moves all of the state that survives across the await into something that's heap allocated. So it can be brought back. And doing all of that work is something that compilers are great at. And so that was sort of the idea that we have this new style of programming where we're using promises or the equivalent of promises and the ability to yield and then we have callbacks. But trying to write your program in that style, that's also what JavaScript suffered from a lot. It's like all this callback style stuff. With Async and Await, you get the illusion that you're just writing normal sequential code and then the compiler does the painful transformation for you. That turns out to be really useful."show more

Announcing: Targeted Spells on Frames When this functionality was... removed going into Midnight, M+ healers including myself expressed how much it impacted the way they played the game. It was such a core and fun layer of information/decision making that was taken away. Over the past weeks, I have been exploring every possible way to restore this functionality within the current UI systems, and after a lot of testing, I finally got it fully functional and 100% accurate. With either EllesmereUI v8.1.3 or the standalone raid frames addon v8.1.3, you will once again be able to see an icon on the party frame of anyone who is being cast on. This is the most excited I've been for any EUI feature, I can't wait for you all to try it. Full Suite: New Raid Frames Standalone: Additionally with this update, the "Casts in front of Nameplates" feature has been re-enabled and is fully functional, showing any casts above all nameplates!show more

‼️ Donald Trump just posted the video saying any... immigrant that comes to America and demand we change our culture is not an immigrant, they are an invader and must be removed “Just so we we’re clear, if a foreigner comes to your country and demands that you accept their culture as your culture or demands that you change your beliefs, that is not a foreigner, that is not an immigrant. What that is, is an invader. That is someone that is coming over to your space to take over and invade it. So when you sit there and you look at what's happening in New York, you look at what's happening in Texas, you look at what's happening in the places where these people came from, you look at Somalia, you look at all of these individuals who are being put into a position of power who support this type of invasion. You need to understand what's coming next. - They will take away our weapons - They will tell us that we cannot eat certain foods - They will tell us that we cannot go to certain places - They will tell that our women that they have to wear certain clothes - They will tell them that they have to dress modest. They will forced them to do a lot of different things. - You will have to deal with people praying in the middle of the street while you're driving and stopping you and invading your movement, your space You need to understand what's taking place in America so that you can understand that these people are not coming here with good intentions. This is not me saying that I hate people. This is me basically saying, look, if you like the fact that America is a free place where you get the freedom to believe in what religion you want to, to believe in. If you get the freedom to decide what you want to do as long as nobody is getting hurt. If you love that part of America, the freedom of choice part of America, you need to understand when people come over and they say that you don't have a choice, they probably should go because you don't get to tell us what to do in our own country. It's not being rude. It's just saying, hey, look, this country was built in a way where everybody can come here and feel happy and feel blessed. And enjoy the fact that this is a free nation, not a nation that will be enslaved by any Foreigner invading it”show more

Computing hardware architecture has evolved from maximizing single-core performance... to multiplying parallel processing capacity through more cores, more threads, and higher computational density. This transition demands software architectures specifically designed to exploit parallel processing, especially in advanced AI and blockchain-based systems. As Greg Meredith, CEO of our partner F1R3FLY. io, notes, "We need software architectures that can eat physical threads of computation and turn that into throughput." Traditional sequential programming models often struggle to effectively leverage the potential of these multi-core systems, creating a bottleneck in performance scaling. Rholang addresses this challenge through its foundation in the Rho-Calculus, a reflective higher-order process calculus specifically designed for inherent concurrency and reflection. Unlike computational models based on sequential execution or those that bolt on concurrency primitives, Rholang can leverage its process-oriented nature to detect and distribute non-interfering logical computation threads across available physical processing units, creating a more direct correlation between hardware resources and performance scaling. The Rho-Calculus was specifically designed to provide the minimal set of operations needed to model autonomous agents operating in parallel while maintaining the ability to represent their own reasoning processes. This structure mirrors the operational characteristics of intelligent systems, where autonomous processes run independently while communicating and coordinating. For our novel decentralized AI platform, MeTTaCycle, this future-proof architectural foundation enables more than just enhanced transactional throughput; it fosters an environment where independent computational processes can efficiently coexist and interact, forming a critical layer for the Artificial Superintelligence Alliance's decentralized AGI infrastructure and products.show more

The same kinds of productivity gains we've seen in... coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.show more

The “everything palette” has been in the back of... my mind for years. I feel that, when correctly automated, it demonstrates an important property of a GUI system, which is an internal interface represented structurally (a common substrate by which all higher level interfaces communicate), and several projections of that interface to higher level interfaces (GUIs, CLIs, hotkeys), such that the internal interface is not substantially duplicated in the projections themselves. Thus, small changes in the internal interface representation immediately and automatically reflect in all such projections. All information for a new setting, for example, is simply expressed in one location, and all interfaces which could access that setting immediately can do so. That setting is automatically accessible in the associated right-click menus, the CLI, hotkeys, and the everything palette. This is because those higher level interfaces are truly *projections* of the underlying interface—they are driven using, in effect, type information of the underlying interface, rather than being special cased to the particulars of the interface (and thus needing to be extensively updated any time the internal interface is changed). The need for this in UI programming is usually first encountered with hotkeys. You write some user interface, and now you need to associate hotkeys—an entirely separate (physical) interface—with the same functionality that your software user interface exposes. You can implement this by, in effect, duplicating the internal interface in both a hotkeys path, and a GUI path. But this is far from ideal for obvious reasons. The debugger by nature enforces this design constraint (GUIs and hotkeys), along with many others, and so it pushed me to follow this to its natural conclusion. A debugger needs to offer an IPC CLI interface for the same commands and features that the main program does. Data in the debugger is already projected in a wide variety of ways—breakpoints can show up in a source view, a disassembly view, a memory view, and a breakpoints list view. My work on the RADDBG visualization engine (driven ultimately by the “watch window” interface—at its limit, a general sparse tree viewer/editor) pushed this even further—you want interfaces to be available through a watch tree evaluation language, as well as several GUIs, and the CLI, and hotkeys. I’ve now finally got the internal systems to the point where they are roughly satisfying all these constraints, and this made the “everything palette” a very simple and natural extension to the system.show more

The next change mentioned in the last AMA on... Discord is the addition of "Mention GPTs" and a more agent-like approach to GPTs This new feature allows you to inline tag any other custom GPT, which will then be displayed as "Talking to [Grimoire/custom GPT name]". This feature also enables using different GPTs in the same conversation, taking an agents-like approach (although it seems that this feature may not work properly yet). To mention a GPT and add it directly into your conversation, simply type "@" followed by the name of the GPT. h/t to Glenn 'devalias' Grant & his amazing ChatGPT Source Watch projectshow more

Krishna on how Anthropic thinks about the platform vs.... application layer, and when they decide to build their own products like Claude Code. It’s the question every investor and founder is thinking about: “Most of what we're building is platform. There's so many examples of where a platform can accrue a lot of value, but the customers who are building on that platform actually accrue even more value. We will build our own applications on that same platform where a couple of things are true. Number one, if we feel like we have a vision into where the models are going and we can demonstrate that and create customer value in that, that might be something like Claude Code. The second is thinking about ways to demonstrate value for the ecosystem that others might emulate. If you think about Claude for financial services or Claude for life sciences, these are ways in which we've composed the platform. We're building on the same platform as our customers. That creates a level playing field. We also think that there's so much value that's going to accrue in these areas that our customers can win and we can win as well. So I think of our strategy as mostly horizontal. A lot of the value is going to accrue to the customers that are building on top of it. Our goal is build the best models and then build the products and tools and services that allow that intelligence to proliferate within customers."show more

It is truly heart warming to return to our... great state and witness the unwavering spirit of its people. While the recent court judgment may not have ruled in my favor, let us remember that our democracy thrives on the principles of justice and fairness. I appreciate the resilience and respect you've shown during this time. As your governor, my commitment to serving the people remains steadfast. Challenges are a part of any journey, and together, we'll overcome them. Let us focus on the common goals that unite us, transcending any temporary setbacks. Our state is more than any individual; it's a collective effort, a shared vision. I am inspired by your support, and I assure you that we will continue working tirelessly for the betterment of our communities. Together, we'll build a brighter future for all, guided by the principles that define our great state. We began this project with God on our side, and by His grace, Plateau will rejoice. We bear no grudges; we have confidence in the Judiciary. Let us continue to uphold the spirit of unity that defines our state, confident that the Supreme Court will be the ultimate arbiter of justice in this matter. Thank you, and let us remain united in our pursuit of a brighter future for all.show more

Open source is dead. That’s not a statement we... ever thought we’d make. Cal.com was built on open source. It shaped our product, our community, and our growth. But the world has changed faster than our principles could keep up. AI has fundamentally altered the security landscape. What once required time, expertise, and intent can now be automated at scale. Code is no longer just read. It is scanned, mapped, and exploited. Near zero cost. In that world, transparency becomes exposure. Especially at scale. After a lot of deliberation, we’ve made the decision to close the core Cal.com codebase. This is not a rejection of what open source gave us. It’s a response to what risks AI is making possible. We’re still supporting builders, releasing the core code under a new MIT-licensed open source project called cal. diy for hobbyists and tinkerers, but our priority now is simple: Protecting our customers and community at all costs. This may not be the most popular call. But we believe many companies will come to the same conclusion. My full explanation below ↓show more

I'm still picking my jaw off the floor with... this MCP update: Postman will now automatically build an MCP server for an API. Automatically! You select your API and the requests you want to include, and Potman will generate a Zip file with everything you need. In collaboration with Postman, I recorded a video showing how I generated an MCP server for the Google Maps API. It's glorious! Also, and before I forget: You can now test any MCP server with your Postman application. They built MCP right in, so now you can: • Connect to an MCP server • List out all of the available tools • Test any of the tools This is a 10x boost for the MCP ecosystem. If you've tried the default MCP debugger, you'll understand how huge a deal it is that you can do all of that from Postman now. Go here to give this a try:show more

wtf is MCP? Paul Klein IV, CEO of explains... "Model Context Protocol" (MCP) in plain terms: "There's this new way that people are exposing tools to AI & the 'Model Context Protocol' is one of those ways that you can standardize & give your AI a set of tools to call. BrowserBase has a way to expose the browser to your agent via MCP or MCP server. More & more developers are trying to find ways to integrate more functionalities to their AI agents & BrowserBase's browsers are one of those primitive functionalities, & the MCP is just one way to integrate it into your software." Paul Klein IV From 🅱️'s GitHub: Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you’re building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need. This server provides cloud browser automation capabilities using Browserbase and Stagehand. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a cloud browser environment.show more

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE... DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems todayshow more