Python · MIT
VecSzn/lobes
An experimental local AI runtime. It relays one request through five small models with one job each, on a single 8 GB consumer GPU.
★ 142
Stars
29 forks · 0 open issues
—
Growth · stale
We stopped seeing this repository in its topic's top results, so its star count is frozen at the date it was last read. Subtracting from a frozen number would read as zero growth, which would be false, so no rate is shown.
18.6
Momentum / 100
see the breakdown below
55d ago
Created
last push 34d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | — — no measurable rate |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 12.4 | last push 34d ago; decays to zero at 180 days |
| Scale | 15 | 6.3 | 142 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 18.6 | capped at 35 because growth is unmeasured |
Detail
| Topics | consumer-gpuggufllama-cppllm-inferencelocal-ailocal-llmmodel-routingon-device-aiopenai-compatible-api |
| Matched on | LLM & Inference (llm-inference) |
| Short window | no snapshot 5–10 days old yet |
| Long window | +18 stars over 26 days = 0.7/day |
| Lifetime average | 2.72 stars/day over 52 days |
| First seen here | 2026-10-11 |
| Last read | 27d ago |