A programmable Mixture-of-Models router for heterogeneous LLM inference
vllm-project/semantic-router is accelerating — star growth is speeding up by +8.9/day (93rd percentile in the tracked cohort), on top of +16.3 stars/day. A recent release is helping fuel the run.
Reconstructed from 237 snapshots — the time-series GitHub’s API doesn’t expose.
Release count rose to 4.
~13 forks/day, 3.5× the trailing baseline.
~12 forks/day, 3.4× the trailing baseline.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/vllm-project/semantic-router)Elevated breakout odds over the next 14 days, led by star acceleration (93th pctl) and momentum score (88th pctl). Confidence is high given the available history.
Transparent heuristic · logged for model training
Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.
~14 forks/day, 3.6× the trailing baseline.
~10 forks/day, 3.8× the trailing baseline.
~12 forks/day, 4.0× the trailing baseline.
~17 forks/day, 3.0× the trailing baseline.
~14 forks/day, 7.8× the trailing baseline.
~13 forks/day, 10.6× the trailing baseline.