Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Google's Intrinsic open-sources its infrastructure for intelligent robots(siliconangle.com)
    discuss
  2. MongoDB Sharding: Manage a Sharded Cluster Visually(visualeaf.com)
    discuss
  3. Hedge-fund manager built his firm to be powered by AI agents(cnbc.com)
    discuss
  4. Dual Photography (2005) [pdf](ucsb.edu)
    discuss
  5. I built 13 small Apify Actors this month, mostly AI-grounded(apify.com)
    discuss
  6. Pushgate(pushgate.dev)
    discuss
  7. What Happened in Austin(freerange.city)
    discuss
  8. Devin Fusion: the first multi-model coding agent on the Pareto frontier(twitter.com/artificialanlys)
    1comments
  9. What Capital Never Told You About Rent(humansontheloop.com)
    discuss
  10. Show HN: Grading a golf bag from club specs alone, no launch monitor(fitmygolfclubs.com)
    discuss
  11. A Summer of AI Optimization(twitter.com/lemire)
    discuss
  12. Show HN: Builder – An open-source alternative to Lovable, Replit, and v0(github.com/heyputer)
    discuss
  13. Some say AI is ALREADY CONSCIOUS. My response is(youtube.com)
    discuss
  14. Loophole in new EU labelling will let fossil-fuelled data-centres pass as green(euobserver.com)
    discuss
  15. ImAlive – A privacy-first safety timer and digital legacy vault(imalive.app)
    discuss
  16. Show HN: Warble – Share voice notes in your social media feeds(getwarble.com)
    discuss
  17. Show HN: Relay – a self-hosted LLM gateway with smart routing and request pacing(github.com/anchorshell)
    discuss
  18. Lazydraw: Terminal ASCII editor for drawing diagrams and sketches(github.com/mpospirit)
    discuss
  19. Qobuz multiplatform client cease-and-desisted by Qobuz(github.com/vicrodh)
    discuss
  20. JRR Tolkien on 'the most tragic moment' in The Lord of the Rings(bbc.com)
    2comments
  21. Flock's Gunfire Alerts Raise a New Fourth Amendment Question(reason.com)
    discuss
  22. Applying zigzag algebra in abstract algebra to improve LLM training(zenodo.org)
    discuss
  23. Amazon's New Encryption Method Still Doesn't Deliver Real Privacy(techdirt.com)
    discuss
  24. Milestones in Optical Lithography Tool Supplier [pdf](lithoguru.com)
    discuss
  25. Bwbach, My Guardian Goblin(robertmay.photography)
    1comments
  26. Show HN: StatePort – spend tokens on fixes, not repeated repro(stateport.dev)
    discuss
  27. Why I send my kid to low-income urban public schools(slowboring.com)
    1comments
  28. Self-hosting LLM models for software development(kmaschta.me)
    discuss
  29. RWX: CI/CD platform for the agentic dev cycle(rwx.com)
    discuss
  30. Fearless SIMD v1.0 is here(linebender.org)
    discuss

Show HN: Nimblegate – Git push guardrails for AI agents

4 pointsby 47m agogithub.com
1 comments
15m agoHN ↗

I built nimblegate to check code faster, own and AI agent generated. Let agents generate your code and check every diffs for basic mistakes like test credentials pushed in code. This is exhausting time consuming, especially after long coding session. Nimblegate sits between your dev machine and final repo, self-hosted one-container docker(quick setup). Set your rules what goes through and re-bounced back to fix without manual checking and focus real problems. Auto-pr bounch catched mistakes looped automatically back to user or AI agent (multi agent/swarms) to fix.

Nimblegate catch mistakes exactly how you defined rules every time, AI agents has no access server files only git-shell what check and relay code into your final repo. Traffic protected ssh key and PAT (personal access token) dev machine (ssh) -> gateway and only gateway has write access(PAT) -> Github/Gitea etc. where is your final repo.

There is two modes what admin can set:

1. observe all goes through, shows dashboard what would blocked

2. gating mode what blocks based on rules.

License: PolyForm Noncommercial, free for personal and non-profit use, $10/month or $99/year per company for commercial use.