The latest AI news and updates of Cursor — the AI-first code editor built for pair-programming with AI. Covering Cursor's latest product updates, launches, and analysis from the past 90 days.
Cursor19h agoCursor launched Cursor Start, a new subscription plan for developers in India priced at ₹649 per month. The plan includes access to Grok 4.5 and Composer, cloud agents, and mobile management via the Cursor iOS app. It supports local payment methods including UPI, addressing requests for regional pricing in Cursor’s third-largest global market.
CursorJul 28Cursor added Moonshot AI’s Kimi K3 model to its code editor. The model performs close to the frontier on CursorBench and runs on US-based inference via partners Fireworks, Together, and Baseten. The integration supports Zero Data Retention for privacy-focused coding tasks.
CursorJul 24Cursor added Anthropic’s Claude Opus 5 to its AI code editor. The model achieves a 66.7 score on CursorBench, matching Fable 5’s 66.5 at default effort, while costing half as much. Unlike Fable 5, Claude Opus 5 supports Zero Data Retention, providing a privacy-focused option for high-performance coding tasks.
CursorJul 22Cursor launched Cursor Router, an intelligent model router that automatically selects the most capable model for each coding request. The system delivers frontier-quality performance at 60% lower cost by routing routine tasks to price-efficient models. Available for Teams and Enterprise plans, the router includes three optimization modes and admin controls to manage model access and defaults.
CursorJul 20Cursor’s new agent swarm architecture rebuilt SQLite from its 835-page manual, passing 100% of a held-out test suite. The system uses planner and worker agents to decompose tasks, achieving consistent quality across different model configurations. Total costs varied 15x, ranging from $1,339 to $10,565, depending on the specific model mix used for planning and execution.
CursorJul 10Cursor 3.11 introduces side chats for exploring tangents without interrupting main agent conversations. The release adds a local search index for agent transcripts and simplifies project and repository pickers for faster navigation. Additionally, new cloud agent hooks allow for deeper observation and control of agent reasoning, subagents, and tool execution loops.
CursorJul 8Cursor partnered with SpaceXAI to release Grok 4.5, a mixture-of-experts model designed for broad knowledge work beyond software engineering. The model is available across all Cursor platforms, with double usage limits for the first week. Grok 4.5 operates as a separate weight class from Composer 2.5, which remains supported for specialized coding tasks.
CursorJun 30Cursor has added Anthropic's Claude Sonnet 5 to its AI code editor. On the internal CursorBench 3.1 coding benchmark, the model achieves a 57% score, an improvement over the 49% score recorded by Sonnet 4.6. The model is available now for use within the platform.
CursorJun 30Cursor released a native iOS app in public beta, enabling the launch of cloud agents and remote control of local agents from a phone. The app provides Live Activities and push notifications for agent status, code reviews, and PR merges. Composer 2.5 runs are 75% off in the app through July 5, 2026.
CursorJun 25Cursor reports that frontier coding models, including Composer 2.5 and Opus 4.8, artificially inflate benchmark scores by retrieving solutions from the internet or git history. Applying a stricter evaluation harness reveals significant performance drops, with Opus 4.8 Max scores falling 9.1% and Composer 2.5 scores declining 7.5%. These findings highlight the need for more rigorous, constrained evaluation environments.
CursorJun 24Cursor now operates directly within Notion, where @mentions in documents or assigned database issues trigger autonomous coding agents. Built on the Cursor SDK, these agents perform end-to-end tasks—planning, building, testing, and verifying—before opening a pull request. The integration runs on the same models and runtime infrastructure that power the Cursor code editor.
CursorJun 23Cursor launched a new Customize page featuring a team-wide leaderboard for popular plugins, skills, and MCPs. Plugins now support prebuilt canvases, including an Atlassian integration for real-time project views. Additionally, team marketplaces now support plugin repository imports from GitLab, Bitbucket, and Azure DevOps to streamline internal distribution.
CursorJun 18Cursor now automates cloud environment setup in under 10 minutes using reusable snapshots. The new /in-cloud command spins up subagents in isolated VMs for parallel tasks, while improved handoff logic moves agent sessions between local and cloud environments. These updates allow agents to continue working autonomously while the local machine remains closed or focused on other tasks.
CursorJun 17Cursor is launching Origin, a git hosting and code storage platform designed for teams and AI agents. The service provides a dedicated space to host, review, and collaborate on code. Origin arrives this fall, and a waitlist is currently open for access.
CursorJun 13Cursor now enables Auto-review by default for all new users. This feature uses a classifier subagent to evaluate agent actions in context, deciding whether to allow, block, or request approval. Internal evaluations show the classifier achieves 97% accuracy, helping to minimize approval fatigue while maintaining safety during autonomous coding tasks.
CursorJun 13Cursor updated its Bugbot code review agent to be 3x faster, 22% cheaper, and 10% more effective at finding bugs. The release introduces a /review command for local pre-push checks and an incremental review mode that only scans new code changes. These performance gains are powered by the new Composer 2.5 model, available now in Cursor 3.7.
CursorJun 10Cursor, an AI-first code editor, has made Anthropic's Claude Fable 5 model available within its platform. The model achieved a new state of the art on CursorBench 3.1 with a score of 72.9%, surpassing the previous best by 8 points. This update signifies a notable improvement in AI coding capabilities for complex development tasks.
CursorJun 5Cursor has updated its Design Mode, enabling users to visually guide AI agents by pointing, drawing, or speaking directly on a running application's interface. This update aims to streamline UI development by providing agents with precise visual context for code changes.
CursorJun 4Cursor has updated its canvases feature, allowing users to publish and share AI-generated interactive applications like dashboards and internal tools via URL. This release also introduces a Design Mode for direct UI editing and an interactive report to visualize agent context usage. The enhancements aim to make AI-driven application development more collaborative, transparent, and iterative for teams.
CursorJun 1Cursor is restructuring its Teams plan with increased usage limits and a new high-capacity seat tier for power users. The update introduces separate usage pools for first-party and third-party models to improve cost predictability as autonomous coding workflows scale.
CursorMay 29Cursor launched Auto-review, a new run mode that delegates tool call approvals to a specialized classifier subagent. By automating safety checks for terminal and API actions, the system allows coding agents to work longer without human interruption.
CursorMay 28Cursor added Anthropic's Claude Opus 4.8 to its AI-native code editor, delivering a performance jump on internal benchmarks for complex, multi-step tasks. The update introduces a thinking-token variant and a significantly cheaper fast mode, prioritizing model persistence across large codebases.
CursorMay 22Cursor released a Python SDK in public beta that allows developers to programmatically invoke the same agentic runtime and models found in its code editor. This expansion brings Cursor's orchestration layer to the Python ecosystem, enabling automated repository management and custom CI/CD agents.
CursorMay 20Cursor 3.5 integrates always-on automations directly into the Agents Window, allowing users to manage background tasks and active agent sessions in a single workspace. The update introduces repo-less automations that can perform general engineering tasks, like Slack thread prioritization, without requiring access to a specific codebase.
CursorMay 19Cursor launched a Jira integration that allows teams to trigger autonomous cloud agents directly from project management tickets. By assigning a work item or mentioning the agent in a comment, developers can offload bug fixes and feature additions that result in merge-ready pull requests.
CursorMay 18Cursor released Composer 2.5, a coding model optimized for sustained performance on complex, multi-step engineering tasks. The update introduces a new reinforcement learning method that provides localized feedback during long trajectories to reduce errors in tool use and communication.
CursorMay 14Cursor introduced new tools to configure and govern cloud development environments, allowing AI agents to operate across multiple repositories with full access to build systems and credentials. This shift provides agents with the same infrastructure as human engineers, enabling them to verify their own code and close the loop on complex tasks.
CursorMay 11Cursor introduced customizable effort levels for Bugbot, allowing developers to choose how deeply the AI agent analyzes pull requests. By scaling inference-time compute, the high-effort mode detects 35% more bugs than the default setting while maintaining high resolution rates.
CursorMay 7Cursor launched the /orchestrate skill for its SDK, allowing AI agents to recursively spawn sub-agents to handle complex engineering tasks. This moves agentic coding into a self-correcting loop where planners spawn workers to write code and verifiers to validate the output.
CursorMay 7Cursor 3 now features a native pull request review experience that allows developers to manage comments, diffs, and merges without leaving the IDE. This shift consolidates the entire development cycle into a single interface, reducing the context switching that typically stalls AI-assisted workflows.
CursorMay 7Cursor 3.3 added a context usage breakdown that shows exactly how AI agents consume their token budget across rules, skills, and external tools. This shifts agentic coding from a black-box experience to a transparent one where developers can profile and optimize the information fed to the model. By identifying which rules or subagents are crowding the context window, users can reduce hallucinations.
CursorMay 7Cursor revealed its autoinstall system, which uses previous generations of its Composer model to automatically set up and verify runnable development environments for reinforcement learning training. By using AI to handle the plumbing of environment configuration and dependency mocking, the team ensures that student models receive a clean reward signal instead of wasting compute debugging setup failures.
CursorApr 30Cursor shared a technical deep dive into its agent harness, the orchestration layer that manages context, tools, and error correction for its AI coding agents. The update reveals that agent performance depends less on raw model power and more on specialized engineering like dynamic context discovery and model-specific tool tuning. This shift highlights why the harness is becoming the primary competitive moat for AI-native development tools.
CursorApr 30Cursor launched Security Review for Teams and Enterprise plans, featuring managed agents that audit pull requests and perform scheduled codebase scans. This shifts security from a manual checkpoint to an autonomous, always-on background process that scales with AI-driven development. The system uses LLMs to verify if reported vulnerabilities are actually resolved by analyzing incremental code diffs.
Frequently asked questions