What it adds

Environment variables it needs 1

LIGHTNING_API_KEY

README

From the reviewed commit e4350ca ↗; it updates when the author re-pins.

lightningai Hermes plugin

Registers Lightning AI (https://lightning.ai/api/v1) as a Hermes model provider (--provider lightningai / lightning-ai / lightning). Models are fetched live from /models.

Disclosure

Registers one model provider at import and nothing else (no tools, hooks, commands or threads).
Chat requests and the model-list probe go to https://lightning.ai/api/v1 (or LIGHTNING_BASE_URL) through Hermes' own client with LIGHTNING_API_KEY, which Hermes reads. The plugin itself opens no connections, reads/writes no files and starts no processes.
Env vars: LIGHTNING_API_KEY (also LIGHTNING_AI_API_KEY), optional LIGHTNING_BASE_URL to override the endpoint.

More by dinosauria123

All 2 plugins by dinosauria123 →

lightningai-rate-limit❖ Community★ 0

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.

Models

← Back to the catalog · catalog built Oct 14, 2026