Categories / Artificial Intelligence
The proxy in front of your LLM should not be the slow part. Rust LLM API proxy: +0.5 ms, 55 MB, same prompt twice costs one call.
agentanthropicasyncbackpressurecircuit-breakerllmllm-servingmcpmodel-context-protocolmulti-agentopenaiorchestrationrate-limitingrusttokio
Created
Oct 2025
Total stars
62
Last 7 days
+1
Last 30 days
+2
Last 12 months
+58
README badge
[](https://rustystars.dev/Mattbusel/tokio-prompt-orchestrator)