Show HN: Log every LLM call with tokens, cost, latency, and time to first token
Hi HN, Llmtee is a lightweight llm proxy. I built this project because I needed a simple way to log llm calls across my agents. Existing options require running Postgres, ClickHouse and Redis, or have me use an SDK. llmtree is just a single binary. You point your provider base url to llmtee, it will pass the traffic through chunk by chunk and log the usage to an SQLite database (or optionally Postgres). The container image is ~25 MB. Memory footprint is around ~40 MB and added latency is ~0.2 ms
Read original source
Source record
Recorded metrics
points · 6 votes
2026-11-13 21:06:37.919Z
cumulative since publication
Research analysis
Project record
Repository: garritfra/llmtee. Source account: Hi HN, Llmtee is a lightweight llm proxy. I built this project because I needed a simple way to log llm calls across my agents. Existing options require running Postgres, ClickHouse and Redis, or have me use an SDK. llmtree is just a single binary. You point your provider base url to llmtee, it will pass the traffic through chunk by chunk and log the usage to an SQLite database (or optionally Postgres). The container image is ~25 MB. Memory footprint is around ~40 MB and added latency is ~0.2 ms
Observed adoption & comparisons
Source votes: 6 votes (Nov 13, 2026 UTC; cumulative since publication) Recent records to compare: “alibaba/open-code-review” (GitHub Trending, Nov 14, 2026); “backnotprop/plannotator” (GitHub Trending, Nov 14, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Adoption decision
Evaluate it against the tool or manual workflow it would replace. The stored record supports discovery; it does not yet establish reliability, lower operating cost or commercial adoption.
Unverified requirements
Not verified: license permissions, required hardware, installation steps, maintenance status and a representative task with its failure cases.
Next test
Choose one real task and a current alternative. Record the commit, environment, input, output, elapsed time and failure behavior; retain the result before recommending adoption.