I was unhappy with bloated #llm proxies, so I built my own: https://garrit.xyz/posts/2026-11-11-introducing-llmteeThe im...

I was unhappy with bloated #llm proxies, so I built my own: https://garrit.xyz/posts/2026-11-11-introducing-llmteeThe image is ~25 MB and Postgres is optional. Memory footprint is around ~40 MB and added latency is ~0.2 ms compared to ~8 ms with #LiteLLM.Try it out right now with:```docker run -d --name llmtee -p 8080:8080 -v llmtee-data:/data -e LLMTEE_ADMIN_PASSWORD=change-me ghcr.io/garritfra/llmtee```Then point #claude at it:```export ANTHROPIC_BASE_URL=http://localhost:8080/anthropicclaude```