Currai
Observability & A/B Testing for LLM Apps
What it does
You shipped your LLM app — now you're debugging it with print(). You can't see what the model actually received, why it answered the way it did, or what each call cost. Currai fixes that: it traces every prompt, token, and tool call in one view, so you can debug and track spend with confidence — and A/B test prompt versions on live traffic to see which one actually wins. Drop in the Python or TypeScript SDK and your first trace lands in ~5 minutes, with zero infrastructure to run.
Does a similar job
all alternatives →- LLLetting LLMs Run a Debugger2025 · github.com · ▲147
Hey HN, I just built an experimental VSCode extension called LLM Debugger. It’s a proof-of-concept that lets a large language model take charge of debugging. Instead of only looking at the static code, the LLM also gets to see the live runtime state—actual variable values, function calls, branch decisions, and more. The idea is to give it enough context to help diagnose issues faster and even generate synthetic data from running programs. Here’s what it does: * Active Debugging: It integrates with Node.js debug sessions to gather runtime info (like variable states and stack traces). *…
- LDLeaping – Debug Python tests instantly with an LLM debugger2024 · github.com · ▲120
Hi HN! We’re Adrien and Kanav. We met at our previous job, where we spent about a third of our lives combating a constant firehose of bugs. In the hope of reducing this pain for others in the future, we’re working on automating debugging. We’re currently working on a platform that ingests logs and then automatically reproduces, root causes and ultimately fixes production bugs as they happen. You can see some of our work on this here - https://news.ycombinator.com/item?id=39528087 As we were building the root-cause phase of our automated debugger, we realized that we developed…
- OOOpenLLMetry – OpenTelemetry-based observability for LLMs2023 · github.com · ▲154
Hey HN, Nir, Gal and Tomer here. We’re open-sourcing a set of extensions we’ve built on top of OpenTelemetry that provide visibility into LLM applications - whether it be prompts, vector DBs and more. Here’s the repo: https://github.com/traceloop/openllmetry. There’s already a decent number of tools for LLM observability, some open-source and some not. But what we found was missing for all of them is that they were closed-protocol by design, vendor-locking you to use their observability platform or their proprietary framework for running your LLMs. It’s still early in the…
- AMA MitM proxy to see what your LLM tools are sendingJan 2026 · github.com · ▲218
I built this out of curiosity about what Claude Code was actually sending to the API. Turns out, watching your tokens tick up in real-time is oddly satisfying. Sherlock sits between your LLM tools and the API, showing you every request with a live dashboard, and auto-saved copies of every prompt as markdown and json.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, June 2026
the whole month →
Fundraisly▲1,544AI fundraising agent that finds investors and books meetings
AI · Jun 2026 · fundraisly.com
- H6Homebrew 6.0.0▲1,481
Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!
Dev tools · Jun 2026 · brew.sh
- PU
hope you enjoy
Life & fun · Jun 2026 · vorpus.github.io
- IM
Life & fun · Jun 2026 · hackernewstrends.com