Leaping – Debug Python tests instantly with an LLM debugger
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…
In plain words
Leaping is a pytest plugin that uses an LLM to debug Python tests by analyzing execution logs in natural language. Developers can interact with it conversationally to understand variable states and behavior over time, similar to an omniscient debugger but at a higher abstraction level. It's designed for teams looking to speed up the debugging process during test development.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
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 something that resembled an omniscient debugger. Like an omniscient debugger, it also keeps track of variable assignments over time but, you can interact with it at a higher level than a debugger using natural language. We ended up sticking it in a pytest plugin and have been using it ourselves for development over the past few weeks. Using this pytest plugin, you’re able to reason at a much higher level than conventional debuggers and can ask questions like: - Why did function x get hit? - Why was variable y set to this value? - What changes can I make to this code to make this test pass? Here’s a brief demo of this in action: https://www.loom.com/share/94ebe34097a343c39876d7109f2a1428 To achieve this, we first instrument the test using sys.settrace (or, on versions of python >3.12, the far better sys.monitoring!) to keep a history of all the functions that were called, along with the calling line numbers. We then re-run the test and use AST parsing to find all the variable assignments and keep track of those changes over time. We also use AST parsing to obtain the source code for these functions. We then neatly format and pass all this context to GPT. We’d love it if you checked the pytest plugin out and we welcome all feedback :) . If you want to chat bugs, our emails are also always open - [email protected]
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 · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d 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 · 26d ago · cactuscompute.com
Launched alongside, March 2024
the whole month →
- 3Y
Life & fun · 2024 · github.com
Microlaunch▲1,116Launch and get feedback on both the idea and product
Dev tools · 2024 · microlaunch.net
