Top all-time · #5048
Ramp Builders
Company blog · builders.ramp.com/postaiprogrammingbusiness
Ramp Builders is the company blog at builders.ramp.com, writing about ai, programming and business. Since 2025, 16 different Hacker News readers have linked it 18 times, most often “Why We Built Our Own Background Agent”. It is still writing: the last post was on 2026-10-22, and you can follow it by feed.
Too few sampled comments (6) to say how often HN recommends it.?
Why HN links it
The Ramp Builders posts describe how Ramp built its background coding agent on OpenCode. HN commenters link the post as an example of agent design, multi-player development environments, and tooling choices.
Summarised by Claude from a sample of 6 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Discover the latest in finance automation that increases the lifespan of businesses from the Ramp team
Most-linked posts?
- Why We Built Our Own Background Agent6 people · 7 mentions · first linked 2026-01-12
- How to Build Agents Users Can Trust2 people · 2 mentions · first linked 2025-07-10
- Forward Deployed Engineering Principles2 people · 2 mentions · first linked 2025-08-06
What Hacker News says?
Author of post here! Ramp Inspect article: https://builders.ramp.com/post/why-we-built-our-background-a... Follow me and ramp Labs on X! Cooking up lots of fun experiments https://x.com/RampLabs https://x.com/a_levitator
Comment linking /post/why-we-built-our-background-agent
on “Building a self-maintaining codebase for 10k users”Submitted Elixir at Ramp as a story · 3 points
HN discussionThis is what I’ve been thinking of ever since coming across Ramp’s agent[1] and other orgs trying to build their own remote dev envs with agents at the center. Makes so much more sense in this kind of a dev spree to not wait for a PR. Because all actors end up repeating the same thing with their own agents which can be totally avoided. Conversations and code to jump in and out of, to collaborate etc seems like the r…
Comment linking /post/why-we-built-our-background-agent
on “Software Is Made Between Commits”Submitted Forward Deployed Engineering Principles as a story · 3 points
HN discussionThis is quite nice but limited in that it is single-player. In my opinion, the next generation of AI agents will be multi-player. Ramp's background agent is a good example https://builders.ramp.com/post/why-we-built-our-background-a... Making this multi-player + creating the right representation to collaborate with agents is in my opinion the next bottlenecks. I wrote a small article about my thoughts there https://…
Comment linking /post/why-we-built-our-background-agent
on “Show HN: Agent-of-empires: opencode and claudecode session manager”Submitted Ramp: How we built OCA, our AI on-call assistant as a story · 2 points
HN discussionramp i think just prebuilts the image/snapshot with the latest checkout version regularly [0]. do you think putting it into the image would address it? [0] https://builders.ramp.com/post/why-we-built-our-background-a...
Comment linking /post/why-we-built-our-background-agent
on “Run isolated sandboxes with full lifecycle control: AWS introduces MicroVMs”Submitted Why We Built Our Own Background Agent as a story · 2 points
HN discussion- ships also as a desktop app - ships with web server that has a UI you can open in your browser, even access remotely with tailscale or so - the server has an API to do almost all things allowing you to build on top of it, the people at ramp build a very advanced internal agent on top of OpenCode https://builders.ramp.com/post/why-we-built-our-background-a...
Comment linking /post/why-we-built-our-background-agent
on “Anthropic Made a Big Mistake”Submitted We built an AI agent that answers 1k data questions a month as a story · 2 points
HN discussionAs an example, this is the exact type of thing Anthropic doesn’t want you to be able to build with Claude & it’s why they want you on their proprietary tooling: https://builders.ramp.com/post/why-we-built-our-background-a...
Comment linking /post/why-we-built-our-background-agent
on “Anthropic Made a Big Mistake”Submitted Forward Deployed Engineering as a story · 2 points
HN discussionSubmitted Building Laminar: Ramp's Managed Agents Platform as a story · 1 points
HN discussionSubmitted Integrations That Write Themselves as a story · 1 points
HN discussionSubmitted Online Learning for Cost-Efficient LLM Routing as a story · 1 points
HN discussionSubmitted Financial Benchmarks – Evaling LLMs on Financial Tasks as a story · 1 points
HN discussionSubmitted How to Build Agents Users Can Trust as a story · 1 points
HN discussionSubmitted How to Build Agents Users Can Trust as a story · 1 points
HN discussion