Automated bug fixing powered by LLMs
Our current demo shows the end-to-end process for a trivial bug fix, but we have been testing it with open source python repos like http-pie, comparing how our agent solves a bug compared to a human engineer and it gets fairly close.
Reactions (1)
Similar products
by description similarity
Leaping
github.comDebug Python tests instantly with an LLM debugger
End-to-End Testing Harness
Modshim
github.comA new alternative to monkey-patching in Python
N0x
n0xth.vercel.appLLM inference, agents, RAG, Python exec in browser, no back end
Aether
news.ycombinator.comBackground agents that fix bugs in isolated VMs, opens PRs