Cursor 3.5: Automations land in the Agents Window with multi-repo + no-repo templates
Cursor 3.5 (May 20, 2026) brings Cursor Automations into the Agents Window, adds multi-repo support so agents reason across multiple codebases, and ships no-repo automation templates in the Cursor Marketplace.
Editorial Team
The Authority AI Tools editorial team maintains this directory using vendor documentation, dated source checks, product changelogs, and clearly identified hands-on observations where available.
Cursor’s 3.5 release (May 20, 2026) is focused on making Cursor Automations a first-class part of the same Agents Window you already use for interactive sessions, plus widening what an automation can be wired up to. (https://cursor.com/changelog/05-20-26)
The AI-native code editor with $1B+ ARR, 25+ models, and background agents on dedicated VMs
This builds on the cursor-3-4-development-environments-cloud-agents-may-2026">Cursor 3.4 development environments release and the earlier Cursor 3.2 Agents Window upgrades, pushing automations away from being a separate surface.
What’s new
Automations in the Agents Window
Cursor says Cursor Automations are now available in the Agents Window, in addition to the existing cursor.com/automations surface. (https://cursor.com/changelog/05-20-26)
In practice, that means you can manage automation runs and ad-hoc agent sessions side-by-side without context-switching between the IDE and the web dashboard.
Multi-repo automations
Cursor describes multi-repo attach for automations: teams can now attach more than one repo to a single automation so agents can reason across all required context and work across repos. (https://cursor.com/changelog/05-20-26)
This pairs naturally with the multi-repo development environments feature from 3.4 — 3.4 set up the environment, 3.5 lets the automation itself span those repos.
No-repo automations
Cursor also introduced automations that don’t require a code repository, so agents can monitor external tools and respond to important signals without being tied to a Git source. (https://cursor.com/changelog/05-20-26)
Five no-repo templates in the Marketplace
Five no-repo automation templates ship in the Cursor Marketplace: (https://cursor.com/changelog/05-20-26)
- Slack digest agent — summarizes Slack messages on a daily cadence.
- Product analytics agent — pulls weekly metrics from data warehouses.
- Product FAQ agent — answers Slack questions using your docs.
- Product finance agent — generates recurring revenue reports.
- Customer health agent — monitors systems like Slack and Databricks.
Promotional pricing for new automations
For the 7 days following the release, Cursor says all agent runs for newly created automations are 50% off. (https://cursor.com/changelog/05-20-26)
Why this matters
Three things stand out for teams already running Cursor at scale:
- One surface for agents and automations. Putting automations in the Agents Window collapses the mental model — runs, history, and ad-hoc sessions live together rather than in two different UIs.
- Cross-repo reasoning. Many real automations (release notes, security sweeps, dependency audits) need to read more than one repo. Attaching multiple repos to a single automation removes a chunk of glue.
- Automations without code. The no-repo templates push Cursor beyond IDE-style work and into the operations layer (Slack, analytics, FAQs, finance, customer health), competing more directly with operational agent platforms.
Sources
- Cursor changelog — 3.5 (May 20, 2026): https://cursor.com/changelog/05-20-26
Tools Mentioned in This Article
Free Resource
2026 AI Coding Tools Comparison Chart
Side-by-side comparison of features, pricing, and capabilities for every major AI coding tool.
No spam, unsubscribe anytime.
Workflow Resources
Cookbook
AI-Powered Code Review & Quality
Automate code review and enforce quality standards using AI-powered tools and agentic workflows.
Cookbook
Building AI-Powered Applications
Build applications powered by LLMs, RAG, and AI agents using Claude Code, Cursor, and modern AI frameworks.
Cookbook
Building APIs & Backends with AI Agents
Design and build robust APIs and backend services with AI coding agents, from REST to GraphQL.
Cookbook
Debugging with AI Agents
Systematically debug complex issues using AI coding agents with structured workflows and MCP integrations.
MCP Server
AWS MCP Server
Interact with AWS services including S3, Lambda, CloudWatch, and ECS from your AI coding assistant.
MCP Server
Context7 MCP Server
Fetch up-to-date library documentation and code examples directly into your AI coding assistant.
MCP Server
Docker MCP Server
Manage Docker containers, images, and builds directly from your AI coding assistant.
MCP Server
Figma MCP Server
Access Figma designs, extract design tokens, and generate code from your design files.
Frequently Asked Questions
What is Cursor 3.5: Automations land in the Agents Window with multi-repo + no-repo templates?
Related Articles
Claude Code 2.1.232: cross-session messaging, forked subagents, and auto mode by default
Anthropic’s August 2026 Claude Code updates add cross-session messaging controls and default subagent forking, while auto mode becomes the default for new Pro, Max, and Team sessions.
Read more →Product UpdatesWarp Agent CLI August update: orchestration, debugging, and Grok connections
Warp’s August 13, 2026 changelog improves the Agent CLI’s orchestration and debugging workflow, adds a /connect-grok command, and fixes long-running command input.
Read more →Product UpdatesGemini 3.7 Flash reaches GA for coding and agent workflows
Google’s August 13, 2026 Gemini API release makes Gemini 3.7 Flash generally available, with a 1M-token context window, coding and agent improvements, and introductory pricing through December.
Read more →