Cursor's Last Six Months - From Editor to Agent Workspace
Six months ago Cursor was an AI code editor. Today it is closer to an agent control room that happens to contain an editor. That shift did not arrive in one release. It came across four of them, and the direction is consistent enough to be worth writing down.
Canonical version: Cursor's Last Six Months - From Editor to Agent Workspace.
Six months ago Cursor was an AI code editor. Today it is closer to an agent control room that happens to contain an editor. That shift did not arrive in one release. It came across four of them, and the direction is consistent enough to be worth writing down.
Cursor became a model lab
The biggest surprise is that Anysphere started shipping its own frontier models. Composer 1 arrived with Cursor 2.0 as a fast, mixture-of-experts coding model. Composer 2 followed in March 2026 and was the first version that read as genuinely frontier-level. Then Composer 2.5 landed in May, matching Claude Opus 4.7 and GPT-5.5 on coding benchmarks at well under a dollar per task.
A code editor training competitive models is not normal. The trick is that all three sit on Moonshot AI's open-weight Kimi K2.5 checkpoint, so Cursor spends its compute on post-training and reinforcement learning instead of building a base from scratch. It works, and it is cheap.
Agents, everywhere
The other through-line is agents, and there are a lot of them now.
- Cursor Subagents (v2.4, January) split a task into parallel pieces, each with its own context.
- Cursor Automations (March) run always-on, triggered by a schedule, a Slack message, or a GitHub event.
- Cursor Cloud Agents graduated to general availability and can now be self-hosted.
- Cursor Multi-Agents run up to eight agents at once, each in its own git worktree.
Cursor 3 made agents the interface
Cursor 3, in April 2026, was the release that committed to the direction. It added the Agents Window, a workspace that shows every agent you are running, local, in a worktree, in the cloud, or over SSH, all in one place. New commands came with it. /worktree isolates a task in its own working copy. /best-of-n runs the same task across several models in parallel and compares the results, which quietly turns model choice into an experiment instead of a guess.
The Agents Window is optional. If you only want Cursor Tab completions and chat, the old editor is still right there.
Customization caught up
As the agents got more capable, Cursor added ways to rein them in. Cursor Skills (v2.4) package domain knowledge into SKILL.md files the agent loads only when they are relevant. Cursor Hooks run scripts at fixed points in the agent loop, so you can block an unsafe tool call instead of hoping a rule discourages it. Cursor Blame labels which lines were written by AI and which by a human, a strange thing to need and an obvious thing to want.
What I make of it
The pattern is clear. Cursor is betting that the unit of work is moving from "a developer editing files" to "a developer supervising agents." Every release in the last six months pushed that way. Composer 2.5 makes running many agents affordable. The Agents Window makes supervising them bearable. Skills, hooks, and Blame make trusting them a little less reckless.
I think the bet is right. The real risk is that supervising eight agents is its own skill, and the tooling is now ahead of most people's ability to use it well.
Related
- Cursor.com
- Anysphere
- Composer 2.5
- Composer 2
- Cursor Agent Mode
- Cursor Multi-Agents
- Cursor Skills
- Cursor Hooks
- Cursor Blame
- Cursor Automations
- Cursor Cloud Agents

About Sébastien
I'm Sébastien Dubois, and I'm on a mission to help knowledge workers escape information overload. After 20+ years in IT and seeing too many brilliant minds drowning in digital chaos, I've decided to help people build systems that actually work. Through the Knowii Community, my courses, products & services and my Website/Newsletter, I share practical and battle-tested systems.
I write about Knowledge Work, Personal Knowledge Management, Note-taking, Lifelong Learning, Personal Organization, Productivity, and more. I also craft lovely digital products and tools.
If you want to follow my work, then become a member and join our community.
Ready to get to the next level?
If you're tired of information overwhelm and ready to build a reliable knowledge system:
- 📚 KM for Beginners — 10+ hours of structured video lessons
- 🚀 Obsidian Starter Kit — Ready-made vault with 40+ templates
- 💼 Knowledge Worker Kit — Complete guides + lifetime community
- 🦉 1-on-1 Coaching — Personalized guidance
- 🎯 Join Knowii — Community + ALL courses & tools
Found this valuable? Share it with someone who needs it.