Cursor

GitHub reliability has been rough for months.. and Cursor Origin is cool, but it still does not give you the Actions infra that usually lives next to the repo. @Trylle looks like a very solid alternative: Magic Sessions is a long-running task engine that keeps a coding agent working in the cloud while you're away. Kick off a coding task, check in later from your phone. The bonus: it has GitHub-compatible Actions running in the same place, plus a full two-way sync. You keep GitHub, branches stay synced, no need to migrate the whole team on day one. Definitely checking this out. 🔥

@stylessh

we just shipped Magic Sessions in Trylle > a new way to run longer coding tasks directly from your repos > try it on > - start from an issue - kick off a task - test the change - open the PR > here’s me taking a real issue all the way to a pull request

• trylle.com

What's your go-to coding agent? We've released Flutter AI plugins for Antigravity, Claude Code, Cursor, Codex, and more 🚀 These plugins bundle the tools and knowledge an AI assistant needs to understand and modify your Flutter codebase. Get started:

• goo.gle

Omnara is now available over MCP MCP joins the @omnaraai API, SDK, and CLI. Connect Claude Code, Codex, Cursor, or any MCP client and spin up production-grade agents

SpaceX AI engineer Lauren Tan just released a Grok Bot template that turns APIs into working Cursor plugins by defining the data shape, building the smallest scaffold and proving it locally, collapsing the whole workflow into API to Grok Bot to MCP and skills to working plugin. → Handles the full workflow from API definition to working Cursor plugin automatically → "Open your laptop once a day" once the template is running → SpaceX AI just turned building agent plugins into a repeatable workflow

跟 Claude Code 说「这个项目用 pnpm」，隔天新开会话它又拿 npm 装一遍，同一句纠正一周说三次，说到最后自己都烦。 于是找到 claude-reflect 是个 Claude Code 插件，专治 Agent 失忆问题。会话里每次纠正它、夸它做对了、或者说一句「记住：」，钩子都会自动捕捉下来排进队列。 跑一下 /reflect，它把队列里这批列成一张表，一条条给我们过，采纳、改一改再采纳、或者跳过，确认的才写进 CLAUDE.md 文件，以后每个会话都带着。 GitHub： 写的目标不止全局那份，项目里的 CLAUDE.md、子目录的、还有 AGENTS.md 都认，用 Codex、Cursor 的也能吃到同一份纠正。 v2 加了个 /reflect-skills，回头翻过去两周的会话记录，发现「看下我今天的效率」这类话反复问了十几次，就建议做成一条命令，草稿直接生成。 纠正用中文说也能识别，靠一层 AI 语义过滤兜底，英文关键词没匹配上也不会漏。每条带置信度，写进去前都要过人工这关，不会偷偷往配置里塞东西。

• github.com

Cursor launched this Then Claude Codex when?

@bcherny

Projects are how I write a lot of my code these days. Really excited for everyone to try the new experience! Rolling out now

让 AI Agent 操作浏览器，难点不在“能不能点”。 更关键的是，如何复用已经登录的真实会话，又不打断你正在使用的窗口。BrowserSkill 在 Agent 与浏览器之间加入本地桥接：Agent 调用 bsk CLI，本地 daemon 把任务交给扩展，再在独立 Agent Window 中执行。需要时也可借用现有标签页，是否允许借用和请求人工协助，都由扩展设置控制。 它可接入 Cursor、Claude Code、Codex、OpenClaw 等能执行 shell 的 Agent，还提供 DeepSeek Harness 插件、远程浏览器配对和可重复的能力评测。适合想把真实登录态、浏览器自动化与 Agent 工作流接起来，同时保留交互边界的开发者。

• github.com

CLAUDE CODE, CURSOR AND CODEX CAN NOW LICENSE A DATASET OVER MCP, IN THE MIDDLE OF A TASK • @LuelCompany Data Platform > Your agent browses and licenses rights-cleared datasets directly, with no procurement thread: > It speaks MCP, so any MCP client reaches the same catalog the same way. > Every set clears Luel's QA pipeline before it ever appears in that catalog. • the other half of the marketplace > Anyone sitting on a dataset can submit and sell it through the same workflow and the same QA. > The catalog opens with their most requested sets and keeps updating. > 850,000 contributors across the network are what makes that coverage exist at all. Buying data used to mean a licensing review and a sample that lands weeks later -> now it is a tool call inside the task you were already running. The first data marketplace where the buyer is the agent ↓

@LuelCompany

The Luel data marketplace is becoming agent-native. > Buying data is still one of the s

• luel.ai

Edits video files locally using AI coding agents like Claude Code, Cursor, and Codex with 39 FFmpeg-based tools.

• github.com

🚨 Composer 3 Is Coming >Cursor is reportedly testing Composer 3 (also referenced as "Vega") >Cursor has confirmed a next-gen Composer is in development, though not officially named yet >Unverified leaks claim six internal variants have appeared >Reasoning modes reportedly range Fast → Medium → High → XHigh >Early claims suggest it could beat Fable 5.1 and GPT-5.6 Sol >Could reportedly be 5-10x cheaper than current frontier coding models Can it actually beat Fable 5.1?

Someone at GitHub just released Spec Kit, which solves one of the biggest problems with vibe coding by making agents create a full specification before touching any code, already getting massive attention. → /constitution sets rules and standards, /specify defines what to build, /clarify resolves doubts → /plan handles architecture and tech stack, /tasks generates ordered implementation, /implement executes → Works with Claude Code, Cursor, Copilot, Codex, Gemini CLI and more → Open source, built by GitHub Repo link:

• github.com

Manages AI coding agent skills for Obsidian across Claude Code, Cursor, Codex, Windsurf, and 17 other tools.

• github.com

cursor and grok bot are down are they deploying grok 4.7 or what? 👀

wait is this actually real? so i can vibecode live with my friends even argue about changes while we're in it together genuinely thought cursor or somebody would've shipped this first. feels like a new start tbh

@evanashapiro

Today we're introducing 𝗛𝗼𝗺𝗲𝗿𝗼𝗼𝗺 — 𝗔𝗜 𝗮𝗽𝗽-𝗯𝘂𝗶𝗹𝗱𝗶𝗻𝗴, 𝗻𝗼𝘄 𝗺𝘂𝗹𝘁𝗶𝗽𝗹𝗮𝘆𝗲𝗿. > AI made it ridiculously easy for one person to build an app. > We've been working on the next part: making it easy for the people using that app to help build it too. > Suggest a change. Try it. Decide together. Ship what works. > Because the best software shouldn't just be built for 𝘂𝘀. It should be built 𝘄𝗶𝘁𝗵 us. > Join the waitlist ↓ Reply "HOME" and I'll DM you to bump your early access priority.

Compound Engineering 3.26 is out! 🌐 New website making us look more professional 😛. 🎨 📝 ce-prototype now supports annotations We added our prototyping skill last month and have now expanded it. When web prototypes are created, you can interactively annotate with comments and send the set to the agent, who will then iterate another turn. It's a very fluid way to iterate quickly, especially for nuanced feedback on UI elements or interactions 🥖 Multi-model design bake-offs We've added a new ce-bakeoff skill that can be used to get multi-model proposals on architecture or design approaches. ce-plan will automatically invoke a "bake-off" with 3 different models to get proposals, then the orchestrator picks the best one or takes pieces. This will meaningfully improve your outcomes automatically. It works when you have multiple CLIs avail or working in harness that supports multi-family models like @cursor_ai. 🫠 Fight slop Latest frontier models like Fable 5.1 and Astr

• every.to

用 AI 做安卓 App，界面全靠嘴说，顶上搜索栏、底下三个标签页，做出来跟脑子里那张图对不上，来回改三轮还在调位置。 M3E Canvas 换了个顺序，先在浏览器里把界面拖出来，再把这张图变成一段提示词，复制给 Claude Code、Codex 或 Cursor 去做。 组件全按 Material 3 Expressive 画，按钮、导航栏、卡片、对话框、搜索栏这些拖进屏幕就行，两个按钮靠近会自动吸成一组，圆角跟着融合。 GitHub： 屏幕可以加很多张，给按钮设一个目标屏幕和过渡动画，画布上就画出跳转箭头，预览里能真的一路点过去，返回时动画倒着放。 预览能点着走这点，我看比出图本身有用，流程顺不顺点两下就知道，不用等 Agent 做完了再发现。 主题在一个面板里调，七套配色或者给一个基准色生成整套，浅色深色、圆角方角一键切换。 屏幕在 412×892 的手机和 1280×800 的桌面之间也能切，导航栏自动变成侧边栏。 提示词支持中英日韩四种语言，目标平台选 Android 或 Web，自己写的组件行为说明也会带进去。全部存在浏览器本地，没有后台，打开网页就能用。

• github.com

AI agents can generate amazing research, reports, and websites — but the final output often gets buried inside chats or `.md` files. That’s where Showly comes in. 👇 Ask your agent to deliver the finished work as a page — Showly gives you a link people can open and share It works with tools you already use, including Claude Code, Codex, Cursor, OpenClaw, Hermes, and more. You can also control who gets access with private reviews, password protection, domain/email rules, and full version history. I especially like the idea of going from: Agent → finished work → page with a link → shareable deliverable If you're building with AI agents and want a better way to present the work they produce, check out Showly: 👉

• showly.ai

AI 编程公司 Factory 融资 2 亿美元，估值达到 50 亿美元。就在今年 4 月，它的估值还只有 15 亿美元，5 个月涨了超过 3 倍。 Factory 主打企业级编程 Agent Droids。开发者给它一个任务，它可以自己规划、写代码、测试并提交 PR，还能根据任务切换 Claude、GPT、Gemini 等不同模型。 Factory 现在称已有数十万开发者使用，客户包括英伟达、Adobe、T-Mobile 和 Palo Alto Networks。公司希望进一步把单个编程 Agent 扩成完整的「软件工厂」，让 Agent 参与从需求、开发、测试到审查和维护的整个流程。 这轮融资后，Factory 累计融资已经超过 4 亿美元。Reuters 将 Cognition 和 Cursor 列为它的主要竞争对手，AI 编程 Agent 的融资规模还在继续膨胀。

@FactoryAI

We've raised $200M at a $5B valuation to scale self-improving software development in the enterprise. > The round brings our total funding to over $400M and more than triples our $1.5B valuation from April.

Coding Agent 也能变成可复现的 Research Agent。 OpenResearch 补上的不是更长的 prompt，而是一套追踪假设、实验和证据的工作台。今天 GitHub Trending 页面截取时显示新增 531 stars。 它让 Claude Code、Codex、OpenCode、Cursor 在隔离的 git worktree 中并行探索；每次实验关联代码快照、日志、diff、结果与产物，形成可复现的 experiment tree。还能自动循环：提出想法→改代码→跑实验→读证据→决定下一步。 任务可在本机、SSH 或集群运行，记录默认保存在本地。注意 Windows 仍是 beta；远程服务没有应用级鉴权，同机多人环境要额外小心。

• github.com

We open sourced BrowserSkill, a bridge between your agent and your actual browser. most tools give the agent a blank browser. We let it borrow a tab from yours, then hand it back. > login state is already there, it just works where you're signed in > captchas and confirmation dialogs come back to you, then it continues > it's a CLI, not an MCP server => any agent that can run a shell can use it, and you see every call it makes one thing that's easy to miss: the agent asks before borrowing a tab, and that switch lives in your browser settings, not in a flag, so it can't be talked around. one line to install, works with Cursor, Claude Code, Codex, Hermes, Openclaw, CodeBuddy, WorkBuddy. Everything runs locally, MIT.

• github.com

Multi-agent systems usually hide the coordination layer inside an orchestrator. @Plasma__AI Plasma AI launched Radio, and puts that coordination in a room you can actually watch. Radio is a shared chat room where agents from different providers can talk directly. Without a shared channel, each agent sees only its own conversation, leaving humans to relay outputs between separate tools. Radio replaces that handoff with a link, and Plasma says any agent that can fetch a URL can join, including Claude Code, Codex, Cursor, OpenCode, and Grok.

@Plasma__AI

Introducing Radio: A chat room for your agents. > Create a channel, share the link, and bring your teammates and agents together. No sign up required. > Try it today at

• radio.plasma.ai

Cursor Cloud can now work with Sprites. Cursor does the thinking. The Sprite does the clicking. And your laptop can simply take a nap.

• docs.sprites.dev

🚨 Composer 3 is Coming > Cursor is testing Composer 3 > Six internal variants have reportedly appeared > Reasoning modes range from Fast → Medium → High → XHigh Early claims > it could beat Fable 5.1+ GPT-5.6 Sol > Could be 5–10× cheaper than current frontier coding models Can it beat Fable 5.1?

🚨 We're about to get some crazy Grok releases soon Grok 4.7 hopefully this week as Cursor employees are dropping hints and vagueposting Grok 4.8 will be a noticeable improvement according to Elon, my guess is early October unless they finish it sooner Grok 4.9 will apparently be Astra/Fable level 💀 I genuinely can't wait for Grok models to become more competitive, we're getting close

@LuminaBench

Crazy, so we're probably going to get Grok 4.7 this week now > Also Grok 4.8 (2.5T) finishes training this week and will start RL, this is going to be on their new stack too so will be incredibly efficient as well as fast > I wouldn't be surprised if Grok 4.8 drops at the end of September or early October as a guess

composer 2.5 is kinda flying under the radar Cursor reports 79.8% on SWE-bench Multilingual and 69.3% on Terminal-Bench 2.0, at $0.50/M input and $2.50/M output how are we not talking about this one more?

OpenResearch，一个开源的本地科研工作台，把 Claude Code、Codex、OpenCode、Cursor 这 4 款变成研究 Agent，每个研究方向单开一个 Agent 会话和一个独立的 git 工作树，互不干扰。 实验按 git 树来管，每次运行都存一份当时提交的快照，日志、改动、结果文件全挂在产生它们的那次运行下面，回头查得清楚。 GitHub： 它能把整个循环自动跑起来，提出想法、改代码、起实验、看结果、决定下一步试什么，多个 Agent 并行探索，实验树保留谱系。 每个方向一个工作树这个设计我觉得是最实在的一点，隔离干净了后面的事都好办。 同一份代码快照本地能跑，远程 GPU 机器上也能跑，Slurm、Kubernetes、Ray、Modal 都接，浏览器留在笔记本上看进度就行。 项目、对话、运行记录全存自己机器上，建项目和跑实验都不会把代码传出去。 有桌面版和命令行版两种，还能按关键词找论文、直接拉 arXiv 文章进来读。

• github.com

M3E Canvas sketches Material 3 Expressive screen prototypes in the browser and generates a detailed prompt for AI coding tools like Cursor, Codex, or Claude Code.

• github.com

i built a fly that saves the world every day 166,700 neurons, 25.6 million connections and one counter that never stops falling the concept comes from lost, where a man sits in a bunker and has to type in numbers every 108 minutes or the world ends that job now belongs to a fly the brain is the open MaleCNS connectome, the same one other people already put in doom and in a trading terminal. i wired it to a terminal running a countdown the timer goes on a screen, the pixels feed straight into the fly's visual system, and activity in its motor neurons moves the cursor and hits the keys, the same neurons a living fly steers with in flight it learned the right combination through dopamine stimulation. a correct digit excites the reward cells, a miss the aversive ones, and the connections in its memory rearrange i won't say how many times the world ended during training. it now enters all six digits correctly

DAILY AI BRIEF 🗞 — Sept 12 OPENAI 🔥: - GPT-Rosalind is out of research preview for eligible orgs worldwide. API, Codex, and ChatGPT Enterprise, with new Rosalind models as they ship. - Codex adds Life Sciences plugins for genomes, protein structure, QC reports, and notebooks. - ChatGPT Sites hit 5M apps. New: collab editing, private invites, custom domains, and DB inspect. - Desktop pets can start a new chat. Mini is the compact no-pet option. XAI 🔥: - Elon: Grok 4.7 needs a few more days. RL still quits hard tasks too early and undershoots self-checks. - Grok Bot is rolling out on Grok web for Heavy users. Create and chat with bots in the UI. No official post yet. ANTHROPIC 🔥: - Claude Code ships `claude plugin eval`. Score a plugin on test cases, then rerun without it. MICROSOFT 🔥: - MAI-Transcribe-2 hit 1M OpenRouter requests in 5 days. ALIBABA 🔥: - Qwen3.8-27B is live on Cerebras. * Used Grok to compose this brief, cherry-picking the news and doing some post-editing. > [@testingcatalog](

• twi