Tag
All content about Cursor, organized for fast scanning.
Cursor has introduced significant updates to its cloud agents, enhancing their capabilities with event-driven workflows and longer session durations, while also launching a new code-hosting platform called Origin that integrates with GitHub. Following its acquisition by SpaceX, Cursor's team will contribute to various AI projects, and the company has increased usage limits for its services, indicating a focus on expanding user access and functionality. Additionally, the rollout of Cursor Router aims to optimize model selection for tasks while reducing costs, reflecting a trend towards efficiency in AI operations.
Cursor has expanded its cloud agents with event-driven workflows, long-lived /goal objectives, and longer-running sessions that can track PRs and Slack threads. The update also adds pinned Custom Modes, smarter steering, and isolated subagent VMs—though questions remain around safeguards and cost.
Cursor has just rolled out Origin, a new code-hosting platform built into its developer tools. The beta starts with GitHub repo syncing plus PRs, merges, and integrations like Vercel and Buildkite. The timing also coincided with a GitHub incident.
Cursor says its acquisition by SpaceX has officially closed, with its team joining SpaceXAI to work on Grok Build, Grok Bot, Grok API, and Cursor. Users are now pressing for clarity on branding, model access, and subscription pricing.
Cursor has just rolled out Cursor Router, an automated model-routing feature designed to pick the best AI model for each task while cutting costs. Teams and Enterprise admins get controls for modes, model access, and optional visibility into the routed model.
Cursor has just rolled out doubled usage limits for individual and team plans, covering Grok, Composer, and “any new Cursor models.” The update comes with refreshed reset timers and 100% cap indicators, sparking questions about permanence and what’s next.
SpaceXAI has just rolled out Grok 4.5, its first model trained specifically for coding and agentic workflows. It targets large codebases and long-running engineering tasks, with aggressive token pricing and claims of faster, more efficient runs. EU access is coming later this month.
Cursor has just rolled out a Notion integration that lets you delegate tasks to Cursor cloud agents right from your docs. The company says it’s built on the Cursor SDK and can even open a PR for team review. The announcement is already drawing plenty of buzz.
Cursor has just rolled out /automate, aiming to turn plain-language tasks into agent-run workflows. It also adds Slack emoji triggers, GitHub triggers for key events, and “computer use” for cloud agents. Early X reactions were positive, with calls for more details.
Cursor has just rolled out Origin, bringing new code storage and git hosting aimed at teams and AI agents. It’s slated for this fall.
Cursor has just rolled out higher usage limits for all Teams users, alongside a new Premium team seat promising “5x usage at 3x the cost.” The move follows Ultra’s momentum, but early reactions question upgrade details and whether the math really saves money.
Cursor has just rolled out auto-review mode, aiming to reduce approval prompts while keeping agent tool calls safer. A new classifier subagent reviews unsandboxed or non-allowlisted actions, deciding whether to proceed, reroute, or ask you first.
Cursor has just rolled out Composer 2.5, calling it its most powerful model yet with better long-task performance and reliability on complex instructions. The company claims up to 10x efficiency and doubled included usage for the next week, though user reactions are mixed.
Cursor has just rolled out a new agent context usage view in Cursor 3.3, aimed at helping users diagnose context issues across rules, skills, MCPs, and subagents. Users are already asking for deeper breakdowns by project, tool, and CLI access.
Cursor has just rolled out Cursor Security Review, bringing always-on code review and scheduled scanning to Teams and Enterprise. It includes a PR-focused Security Reviewer and a Vulnerability Scanner that can post findings to Slack, with customizable triggers and tooling.
Cursor has just rolled out /multitask in Cursor 3, letting async subagents run in parallel instead of queueing. The update also adds improved agent worktrees and multi-root workspaces for cross-repo changes, available in Cursor 3.2.
Cursor has just rolled out new quality-of-life updates to its CLI, led by a new /debug flow for tackling hard-to-reproduce bugs. It also adds /btw for side questions, a built-in /config panel, and customizable /statusline indicators.
Cursor has rolled out interactive canvases, letting its AI respond with visual, clickable layouts instead of just text. The goal: generate dashboards and custom interfaces without leaving the editor. Early reactions praise faster scanning, while others flag workflow quirks.
Cursor has just rolled out learned rules for Bugbot, turning real PR feedback into continuously updated review behavior. The company says Bugbot’s suggestions are now addressed nearly 80% of the time before merge, up from 52% at launch.
Building agentic coding systems often fails on a familiar constraint: you can make them fast, or you can make them smart—but professionals need both to stay in flow. This talk walks through how Cursor built Composer, focusing on the infrastructure, training setup, and evaluations behind a low-latency coding agent model. Breaks down the “fast vs. smart” trade-off and why token-generation efficiency matters in real workflows Explains the rollout-based RL setup, including how tool calls (read/edit/search/lint/shell) are used and scored Covers scaling challenges like bursty compute, consistency between training and production, and load balancing for uneven rollouts Shows why matching the production environment—and integrating semantic search—shapes stronger agent behavior (e.g., better search/read before editing)
If you’re weighing Claude Code versus Cursor (or trying to juggle both), this walkthrough shows what changes when Claude Code is fully integrated inside Cursor—so you can work with live context without constantly re-explaining your code. Key takeaways Walks through setup in Cursor’s integrated terminal: updating Claude, signing in, and confirming the integration. Shows how the status indicator reflects the active file, enabling prompts like “what does this file do?” without naming it. Demonstrates line awareness: select a block of code and ask “what does this do?” with the selection as context. Breaks down the diff view workflow—review proposed changes, revert specific blocks, and accept/reject (with an optional auto-accept toggle), plus linking Cursor from an external terminal via /ide.
If you’re tired of Cursor (or any other AI editor) breaking your code with random errors, this video is for you. I’ll show you how I used Task-Coding to fix 90% of the issues that come from vibe-coding. This method gives Cursor clear structure, better context, and way fewer mistakes. Watch me build a full app with multiple pages, charts, and auth—error-free. Might be worth noting that using the MAX mode can eat up your costs. You get billed per token for the full context window of the entire chat. There are a few other chat models that you can use without being on MAX mode that still have a great context window, such as the gemini models. GH Repo: https://github.com/eyaltoledano/claude-task-master
Vibe coding can feel fast—until your agent starts drifting from your stack, bloating context, or “fixing” bugs by rewriting everything. This tutorial breaks down how the speaker uses agentic coding in Cursor or Windsurf to push more work end-to-end onto an AI agent, while staying in control as the codebase grows. Walks through a concrete setup: choosing models and adding custom models via an overridden API key/base URL Shows why a detailed spec matters, and how they generate one separately before pasting it into the IDE Explains how Cursor/Windsurf “rules” guide tech choices, workflow, and scope to avoid unwanted rewrites or duplicate code Shares practical habits: managing context size, keeping requests narrow, favoring end-to-end tests, and committing/restoring checkpoints often
Learn how to integrate Claude Code 4 with Cursor in this step-by-step tutorial. This new feature from Anthropic brings full Claude Code support to the Cursor AI IDE, giving you new features, like inline diff views and real-time code context, all within your favorite IDE. I’ll walk you through the setup process for Cursor and explain key features that make this integration of the best AI coding agent upgrades yet.
Handing off work—or keeping yourself aligned—gets messy fast when the “task” lives across chat threads, docs, and half-finished TODOs. This video walks through how the speaker uses a tasklist.mdc Cursor rule to define and execute real feature work in an open-source project (Inbox Zero), while staying clear-eyed about where AI helps and where it doesn’t. Key takeaways How tasklist.mdc is used to generate a structured task file (completed / in-progress / future tasks, implementation plan, relevant files). How to seed Cursor with the right context by tagging specific files and UI/email wireframes. What it looks like to iterate when the first AI output is “roughly OK” but includes mistakes—and how to correct it. How PR review tooling (CodeRabbit) fits into the workflow as an extra set of eyes.