Showing the last saved plugin snapshot.

← Leaderboard / Models / Plugin
Last repository activity November 10, 2026 · Created October 28, 2026

Clawz1N1N/dsh-llm-model-rate-limit

“Per-model request and token rate limits for DeepSeek Harness.”

Star rank
#6034
declared plugin rank
In Models
#722
category rank
Stars
1
GitHub repository
Forks
0
GitHub repository
Watchers
0
GitHub subscribers
Open on GitHub ↗
TL;DR

Per-model request and token rate limits for DeepSeek Harness: rolling windows, FIFO idle waiting, and 429 backoff without stopping the model.

30 days of GitHub stars
+0 stars
+0% observed change
Oct 14Oct 28Nov 12