We have lots of benchmarks for new frontier LLMs (SWE benchmarks etc) to make them score on the "best code". In large codebase, the best code is the one that ma
Opens https://argot.tmonier.com/
As someone who is using agents to code for me a lot lately, I was starting to feel more and more like I'm losing touch with the code I write--it's starting to f
I’d be glad to hear what you think, including where you disagree, and answer any questions
I built Isolade because I could not find an open-source, local-first workbench that runs coding agents in microVMs.The two pieces already exist individually. Th
Hi HN! We’re Theodore and Louis, founders of Armature (YC P26). We reconstruct the entire session behind the MCP tool calls you receive, including what the user