Keep coding agents running autonomously for long stretches
Documented elsewhere: cursor ran hundreds of concurrent agents on one project. Flat self-coordination through a shared file with locks, then optimistic concurrency, failed. A browser assembled from scratch ran close to a week and produced over 1 million lines across 1,000 files.
- Agent or tool
- Cursor
- Topic
- Software Development
- Reported on
- Hacker News
- Added
- 2026-10-15
Why it matters
Coding agents are moving from autocomplete to doing whole tasks: reading a codebase, making a plan and changing many files. This case is a concrete example of where that works in practice. It is one of 106 sightings filed under Software Development on Agent Sightings (number 11 by interest), and one of 30 involving Cursor.
How you could try it
Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into Cursor or any similar agent and adjust the details to your situation.
In this repo, keep coding agents running autonomously for long stretches. Read relevant code, apply a minimal patch, run available checks, and summarize the diff. Stop before merge or deploy.
The prompt breaks down into 3 steps you can check as the agent works:
- In this repo, keep coding agents running autonomously for long stretches.
- Read relevant code, apply a minimal patch, run available checks, and summarize the diff.
- Stop before merge or deploy.
Tip: Work on a fresh branch, ask for a plan before edits, and review the diff and test results before merging.
Source
Read the original first-hand account on Hacker News: https://news.ycombinator.com/item?id=46624541. Our summary is a paraphrase; details are in the source.