SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

Pure Java ZeroMQ

ZeroMQ core engine in C++, implements ZMTP/3.1

command argument completion generator for spf13/cobra

A Commander for modern Go CLI interactions

Powerful scripting language & versatile interactive shell

33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU

Access large language models from the command-line