princeton-nlp/SWE-agent
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.
PythonMIT
Watchers
- akan
- appdotdotOak Indoor Climate Technologies Co., Ltd.
- bmorphism@plurigrid
- bmwas
- carlosejimenez@princeton-nlp
- chaiyuntianProgrammer & Art Enthusiast
- danqiPrinceton University
- djwackeyChina, Beijing
- dogmaticwonder
- ecfmMIT Sloan
- erickmillerCoinCircle
- gastonfeng
- godlikeldh
- GoZippyZippy Networks
- janevin
- jwcraig
- kervinpierreCityMSP
- kushaank
- kwseow
- lecharles@salesforce
- lgshttp://www.linkedin.com/in/lucasoave
- liuquan0722
- ljw031129
- mbrownnycnyc
- mikanfactoryTokyo
- myousefiNortheastern University
- mznMzn Software & Robotics Technologies
- nikete
- NxNikiUCLA
- rsc1975Laude Technology
- SashaOvLinkedIn
- snowskyOpenNMS
- wangvnnWangvnn
- xiaoxisun
- ysymythPrinceton University
- yunshangcao26