Top all-time · #15026
Laminar
Company blog · laminar.sh/blogaiprogramming
Laminar is the company blog at laminar.sh, writing about ai and programming. Since 2025, 5 different Hacker News readers have linked it 7 times, most often “Show HN: We instrumented Claude Agent SDK using a tiny Rust proxy”. No feed was found, so read it on the site itself.
Too few sampled comments (3) to say how often HN recommends it.?
Why HN links it
HN readers link Laminar's blog for agent observability write-ups, including a flow-1 post with examples of traces and errors it caught in agent runs. Other comments mostly describe the product and its approach.
Summarised by Claude from a sample of 3 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Open-source platform to trace, evaluate, and debug AI agents. Laminar surfaces agent failures, and helps you fix them.
Most-linked posts?
- Show HN: We instrumented Claude Agent SDK using a tiny Rust proxy2 people · 2 mentions · first linked 2025-12-04
- Extracting Tasks from Millions of Agent Runs2 people · 2 mentions · first linked 2026-10-02
What Hacker News says?
Sometimes, it gets to very hacky solutions, such as what we did at Laminar with Claude Agent SDK. Basically we spin up a tiny in-process proxy that intercepts requests and responses and emits the telemetry as OTEL traces. We repoint the Python / JS SDK to convince the harness that our proxy is the anthropic URL, and the proxy then forward the request downstream. I wrote about it some time ago [1]. This is definitely…
Comment linking /blog/2025-12-03-claude-agent-sdk-instrumentation
on “If you don't run your own LLM proxy, how do you know whats going on?”Submitted Extracting Tasks from Millions of Agent Runs as a story · 6 points
HN discussionthis is exactly what flow-1 in Signal harness catches. highly highly recommend checking this out https://laminar.sh/blog/flow-1-in-action . We got examples of traces and errors we caught in them there
Comment linking /blog/flow-1-in-action
on “Launch HN: Laminar (YC S24) – RL-trained model that finds errors in agent traces”Submitted Show HN: We instrumented Claude Agent SDK using a tiny Rust proxy as a story · 6 points
HN discussionGood questions. Agent observability is based on similar primitives as regular observability (OTEL), but is wildly different. Trace payloads are huge, and errors are much more subtle, they are not increased latency or elevated 500 response rate. We recommend tracing everything in detail, and reading a few traces manually at the beginning while you iterate. At scale, the answer is almost always use another LLM look at…
Comment linking /blog/extracting-tasks-from-agent-runs
on “Launch HN: Laminar (YC S24) – RL-trained model that finds errors in agent traces”Submitted Flow-1: Frontier trace intelligence at 1/20th of the cost as a story · 2 points
HN discussionSubmitted Show HN: Rebuilding My First Startup with Claude Agent SDK as a story · 1 points
HN discussion