All plugins

lightningai-rate-limit

Per-process throttle for Lightning AI (https://lightning.ai/api/v1) keeping LLM requests within the ~15 requests/min limit, using an in-memory token bucket. Gates only calls whose provider or base_url points at Lightning AI; no-op otherwise. Disclosure — registers one llm_execution middleware and nothing else; no network calls, files, or processes of its own.

dinosauria123Modelsv1.1.0Updated 1 month ago

About

Per-process throttle for Lightning AI (https://lightning.ai/api/v1) keeping LLM requests within the ~15 requests/min limit, using an in-memory token bucket. Gates only calls whose provider or base_url points at Lightning AI; no-op otherwise. Disclosure — registers one llm_execution middleware and nothing else; no network calls, files, or processes of its own.

lightningai-rate-limit Hermes plugin

Per-process token bucket that keeps Lightning AI requests to <=15/minute.
Middleware registered as llm_execution; activates only when the active
provider/base_url points at Lightning AI.

Disclosure

  • Registers one llm_execution middleware and nothing else.
  • No network, files, or processes of its own. In-memory lock only.

README from the reviewed commit dc7911a; it updates when the author re-pins.

More by dinosauria123

2 plugins by dinosauria123 in the catalog.

Developer Mode

Explore built-in Hermes toolsets and actions.

HermesAgent

Developer?

Create a Hermes extension for Desktop or agent workflows.

Developer Section