Cursor's planner-worker agents built a web browser from scratch in about a week
Cursor tested long-running autonomous coding with a hierarchy of planner agents that create tasks and worker agents that just complete them. The headline project was a browser engine, published as FastRender.
The problem
Single agents stall or lose track on very large codebases. Cursor tried to find an agent structure that keeps hundreds of agents productive on one repository for weeks.
How they did it
- Planner agents explore the codebase, create tasks and start sub-planners for specific areas.
- Worker agents focus on finishing their assigned task and don't coordinate with each other.
- Every agent pushes to the same branch.
Results as reported by Cursor
- The agents ran for close to a week, writing over 1 million lines of code across 1,000 files.
- Hundreds of workers run concurrently, pushing to the same branch with minimal conflicts.
- Other runs included a Solid-to-React migration in Cursor's own codebase (+266K/-193K edits), which the team says still needs careful review.
These figures are as reported by Cursor in Cursor Blog ↗ (Jan 14, 2026). Cursor sells the product used here. AgentGid did not measure or independently verify them.
This is a research-scale experiment, not a workflow to copy: running hundreds of concurrent agents for a week suits teams with deep engineering skill and a large model budget. Cursor's plans bill usage at model API rates with on-demand overage, so costs at that scale could climb fast. For smaller-scale agent work, Zed (open source, Free + $10/mo) lets you bring your own API keys.
The agent used here
Similar use cases
IMDEX built a mining data platform in 8 months with Cursor
IMDEX, an Australian mining technology company, used Cursor to merge fragmented geological data products into one platform and to move a legacy Angular app to a React micro fronte…
The data platform landed in eight months; without Cursor it would have taken 20 additional engineers, two to three years and millions of dollars, as …
How National Australia Bank sped up legacy migrations with Cursor
NAB engineers used Cursor to understand and migrate legacy Silverlight/.NET and Assembly systems, and to build a new payment app. As reported by Cursor, delivery was well ahead of…
As reported by Cursor: NAB 'originally scoped six months of work' for the BizCalc migration and now expects it to finish in two months, 'a 3x improve…
Navan cut a month-long Spring Boot migration to a week with Cursor
Navan, the business travel and expense management company, ran its latest Spring Boot upgrade with Cursor's Cloud Agents: a senior engineer planned the migration once and handed e…
A Spring Boot migration across 8 applications and 15 libraries finished in about a week, against over a month for a comparable migration two years ea…
Guides
Malicious Claude Code 2.1.312 and 2.1.313 Extensions in Cursor: What It Did and How to Check
Tampered Claude Code extensions, versions 2.1.312 and 2.1.313, sat in Cursor's extension marketplace on October 29, 2026 and tried to plant an SSH backdoor. What Cursor's notice confirms, why the tunnel mostly failed, and how to check and clean a machine.
How to Cut Token Usage in Claude Code and Cursor (2026)
Practical ways to spend fewer tokens with Claude Code and Cursor: measure first, keep context small, match the model to the task, filter what the agent reads, and the open-source tools that help.
VoiceStudio: The Free, Local ElevenLabs Alternative
A viral post calls VoiceStudio a 100% free ElevenLabs replacement with 19.4K stars. We checked it against GitHub and the project's own pages: what it does, what is really free, the license catch in the default voice model, and how to plug it into Claude Code or Codex.
AI Coding Agent Pricing Explained: Claude Code, Cursor, Codex and Copilot (2026)
What Claude Code, Cursor, OpenAI Codex, GitHub Copilot and other coding agents really cost: plan prices, usage limits, subscription vs API billing, and how to estimate your monthly bill.