Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #8882

C

Charlie Labs

Company blog · charlielabs.ai/blog · on HN as rileytaiprogramming

Charlie Labs is the company blog at charlielabs.ai, writing about ai and programming. Since 2025, 9 different Hacker News readers have linked it 21 times, most often “Show HN: Daemons – we pivoted from building agents to cleaning up after them”. It is still writing: the last post was on 2026-09-21, and you can follow it by feed.

Visit the blog
21mentions?
9HN people?
2025–2026first – last linked?
Links on Hacker News per year · peak 17 in 2026

Too few sampled comments (5) to say how often HN recommends it.?

Why HN links it

The comments are product pitches for Charlie, a cloud coding agent, linking its pricing, how-it-works and docs pages and asking for feedback. None discuss the writing.

Summarised by Claude from a sample of 5 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

Daemons are always-on AI processes that work proactively across Slack, Linear, GitHub, and more. Defined with simple .md files.

The author on HN?

rileyt · 643 karma · member since 2012

Founder of charlielabs.ai

From their public HN profile, which links to this site.

Most-linked posts?

  1. Show HN: Daemons – we pivoted from building agents to cleaning up after them
    2 people · 2 mentions · first linked 2026-04-21

What Hacker News says?

  1. At my company (Charlie Labs), we've had a tremendous amount of success with context awareness over long-running tasks with GPT-5 since getting access a few weeks ago. We ran an eval to solve 10 real Github issues so that we could measure this against Claude Code and the differences were surprisingly large. You can see our write-up here: https://charlielabs.ai/research/gpt-5 Often, our tasks take 30-45 minutes and ca…

    Comment linking /research/gpt-5

    on “GPT-5 for Developers”
  2. Submitted Show HN: Daemons – we pivoted from building agents to cleaning up after them as a story · 12 points

    HN discussion
  3. We just came out of closed alpha yesterday and have been trying to figure out how best to price, if you'd be willing to provide any feedback I'd certainly appreciate it: https://www.charlielabs.ai/pricing - Thank you!! :)

    Comment linking /pricing

    on “Anthropic tightens usage limits for Claude Code without telling users”
  4. Submitted Coding Agents as Operating Systems as a story · 7 points

    HN discussion
  5. We are building a tool specifically for typescript developers, just launched a couple of months ago and I'd really appreciate if you gave it a try and provided me with feedback, people seem to really like using it. http://charlielabs.ai - thank yooou!!! :)

    Comment linking /

    on “I tried vibe coding in BASIC and it didn't go well”
  6. Submitted The End of Local as a story · 3 points

    HN discussion
  7. Okay, but like I said before in another comment, I have spent 3 days straight coding, neglecting myself and everything around me in the process. I was learning a lot, coding a lot. I was productive. Of course I should have had some breaks (for my legs and mind, and my body). Just make sure to have breaks. I did not have breaks because I was completely zoned in. I set up a timer by then that remind me to take a break…

    Comment linking /

    on “OpenAI's "Study Mode" and the risks of flattery”
  8. Submitted For agents, there really are dumb questions as a story · 3 points

    HN discussion
  9. tl;dr : https://charlielabs.ai/how-it-works/ and https://docs.charlielabs.ai/daemons to get started, look at https://docs.charlielabs.ai/installation , but essentially 1) signup with your github login 2) install the CharlieCreates GitHub App on the repos you want Charlie to work in 3) create an issue, tag @CharlieHelps to help you create your first daemon! the daemon will run on the charlie runtime and follow the wa…

    Comment linking /how-it-works/

    on “Show HN: Daemons – we pivoted from building agents to cleaning up after them”
  10. Submitted Claude just discovered workflows. Charlie started there as a story · 2 points

    HN discussion
  11. That's exactly right. Our cloud-based agent Charlie ( https://charlielabs.ai/ ) supports this, and our hope is that other platform providers will offer support in the future as well. Skills live in the repository, so it felt like a natural complement. It also lets other developers see what the active daemons are and collaborate on them. With proper context, agents are quite good at writing and editing these daemon f…

    Comment linking /

    on “Show HN: Daemons – we pivoted from building agents to cleaning up after them”
  12. Submitted Repo sets the rules. Charlie runs the review as a story · 1 points

    HN discussion
  13. Submitted The challenges of building a reliable PR review agent as a story · 1 points

    HN discussion
  14. Submitted HubSpot wanted me to talk to sales, so I built my first prod. system in 10 years as a story · 1 points

    HN discussion
  15. Submitted I rage-built email automation because HubSpot wanted me to talk to sales as a story · 1 points

    HN discussion
  16. Submitted 90% cheaper repo inference with GPT-5.4 nano as a story · 1 points

    HN discussion
  17. Submitted Don't ask if it works. Ask for proof as a story · 1 points

    HN discussion
  18. Submitted Multi-player agents are the future as a story · 1 points

    HN discussion
  19. Submitted The Tast Supply Problem as a story · 1 points

    HN discussion
  20. Submitted Why the next agent interface is shared as a story · 1 points

    HN discussion
  21. Submitted The Coding Agent OS as a story · 1 points

    HN discussion

Search all of HN for charlielabs.ai