SWE-agent takes a GitHub issue and tries to automatically fix it
SWE-agent turns LMs (e.g. GPT-4) into software engineering agents that can resolve issues in real GitHub repositories. On the SWE-bench, the SWE-agent resolves 12.47% of issues, achieving state-of-the-art performance on the full test set. We accomplish our results by designing simple LM-centric commands and feedback formats to make it easier for the LM to browse the repository, and view, edit, and execute code files. We call this an Agent-Computer Interface (ACI).
AI Agents Masterclass is an educational open-source repository designed to teach developers how to build, train, and deploy intelligent AI agents using modern tooling and workflow patterns. The project includes structured lessons, code examples, and practical exercises that cover foundational concepts like prompt engineering, chaining agents, tool usage, plan execution, evaluation, and safety considerations. It breaks down how autonomous agents interact with external systems, handle...
This software presents a flexible and configurable proposal for monitoring and management of real and virtual HPC infrastructures, compatible with paradigm of cloud computing.
We help you to answer:
1) What is the performance of my resources?
2) What equipment and resources do we have already?
3) What do we need to upgrade or repair?
4) What can we consolidate to reduce complexity or reduce energy use?
5) What resources would be better reused somewhere else?
Status: PreAlpha, so any help shall be welcome.
Made for LINUX.
GNU General Public License version 3.0 (GPLv3)