News for hackers. Stuff that matters.

NomiJ

NomiJ on Hacker News

Re:Show HN: Helix – open-source self-healing back end for production c... on Wednesday April 15, 2026 @11:52AM (#47780869)
Fair point. I was not aware of Helix Editor when I named the project. That is my mistake. The project is early enough that renaming is still possible if it becomes a real issue. Would you recommend a rename now or wait to see if the name collision actually causes confusion?

Show HN: Helix – open-source self-healing back end for production crashes

Posted by NomiJ on Wednesday April 15, 2026 @05:07AM
from the show-hn dept.

https://88hours.github.io/helix-community/

Six months ago I got tired of being woken up at 3am for bugs I already knew how to fix.So I built Helix. Bug hits Sentry. A multi-agent pipeline kicks off. QA agent writes the failing test first (TDD). Dev agent writes the minimum fix, runs the full suite, opens a PR. You get a Slack message with one button to approve.Crash to merged PR in under 10 minutes.

( Read More... | 4 comments | 2 points | on HN )
Re:Show HN: Self-Healing Back End That Does TDD on Tuesday April 14, 2026 @10:16AM (#47765978)
Helix watches your error tracker (Sentry or Rollbar). When a bug hits production, a pipeline of agents kicks off automatically: 1. Crash Handler agent parses the webhook and extracts context 2. QA Agent follows test driven development approach and writes a failing test then opens a GitHub Issue 3. Dev Agent clones the repo, writes a fix for failing test, and creates a PR. 4. Notifier sends the issue + suggestion to Slack for human review with "Approve PR" or "Reject PR" options.

Built with Python, Redis pub/sub for the event bus, and Claude (or Ollama if you prefer local). Self-hostable via Docker Compose.

GitHub: https://github.com/88hours/helix-community

Happy to answer questions about the agent architecture or how the fix suggestions are generated.

Re:Show HN: Helix – open-source self-healing back end for production c... on Saturday April 11, 2026 @10:11AM (#47730785)
It also ship Helix as a Claude skill, so if you are already using Claude Code or Cowork you can get the whole pipeline running in one install with no manual config.

Show HN: Helix – open-source self-healing back end for production crashes

Posted by NomiJ on Saturday April 11, 2026 @09:56AM
from the show-hn dept.

https://88hours.github.io/helix-community/

Helix watches your error tracker (Sentry or Rollbar). When a bug hits production, a pipeline of agents kicks off automatically: 1. Crash Handler parses the webhook and extracts context 2. QA Agent follows test driven development approach and writes a failing test then opens a GitHub Issue 3. Dev Agent clones the repo, writes a fix for failing test, and creates a PR. 4. Notifier sends the...

( Read More... | 1 comment | on HN )
Re:Show HN: We moved from AWS to Hetzner, saved 90%, kept ISO 27001 wi... on Thursday July 03, 2025 @10:53AM (#44455679)
100% this. I have used support multiple times, there were times when calls took more than 12 hours. We used basic and Whenever I needed support I turned on to "Business" - from memory it costed 100 bucks a month.
Re:Ask HN: Show me your half baked project on Sunday October 22, 2023 @11:50PM (#37981423)
chatGPT at backend?