swe-serve
SWE-Serve: an agentic benchmark of 53 production inference-engineering tasks derived from merged SGLang pull requests, run with Harbor.
SWE-Serve evaluates LLMs/agents on production inference engineering tasks. The benchmark includes 53 tasks derived from recent production changes to SGLang: 41 GPU (H100) tasks and 12 CPU tasks. Tasks test correctness, including integration into an inference system through end-to-end execution, persistent state, or concurrent requests.
⚡ How to use swe-serve
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/nvidia-swe-serveCapabilities
Do you own swe-serve?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.