llmbridge
A sub-millisecond, drop-in OpenAI-compatible LLM gateway in C++
We run llmbridge inside the AI gateway reproducible benchmark by Jakub A. Wąsek of ENTERPILOT, the author of GoModel: every gateway from its public Docker image, one at a time, against the same in-memory mock, 20,000 requests per variant at concurrency 10, five trials in randomised order, a separate throughput sweep. Chat completions, added p50 over the harness's no-gateway baseline, one llmbridge worker, reference laptop:
⚡ How to use llmbridge
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/kottos-ai-llmbridgeCapabilities
Do you own llmbridge?
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.