README

From the reviewed commit cab5372 ↗; it updates when the author re-pins.

hermes-kame-provider

Hermes asks a provider profile for its model client before it builds its own (ProviderProfile.create_client, and create_messages_client for Anthropic Messages endpoints). This model-provider plugin registers, for every bundled API-key provider, a profile that inherits everything from Hermes' own — endpoints, models, auth, request shaping — and adds only those two client factories, which ask hermes-kame-api-rotation for a client that rotates the provider's keys on every request: Chat Completions, Responses API and Anthropic Messages.

Nothing in Hermes is replaced, wrapped or rebound: the bundled profile objects are copied into new ones, and Hermes' own registry keeps them as the documented per-home override.
Without hermes-kame-api-rotation installed and loaded for the same profile home, or with KAME switched off (KAME_ROTATION_DISABLED=1), both answer None and Hermes builds its own client exactly as it always does. A Hermes that does not yet ask create_messages_client builds its own Messages client; the other wires still rotate.

hermes plugins install Kame696/kame-api-rotation-for-hermes/hermes-kame-api-rotation
hermes plugins install Kame696/kame-api-rotation-for-hermes/hermes-kame-provider
hermes plugins enable hermes-kame-api-rotation

Restart Hermes once after installing. MIT licence.

More by Kame696

All 2 plugins by Kame696 →

hermes-kame-api-rotation❖ Community

Smart API key rotation: the healthiest key for every call, each 429 / RESOURCE_EXHAUSTED / quota refusal sized from its own evidence. Install with its companion hermes-kame-provider, which hands Hermes this plugin's rotating client through ProviderProfile.create_client (and create_messages_client where Hermes offers it); no core override. Disclosure — /kame-keys add|import|split, and on start a key variable holding several comma-joined keys, write one auth.json pool row per key through Hermes' pool API after a plaintext backup (last 5 kept; switch: resolver_disabled); key-redacted, size-capped owner-only local logs and a status file per profile; the Desktop panel reads that file and queues its settings requests through its own dashboard/plugin_api.py route (GET /state, POST /control, this plugin's plugin-data folder only); while every key is resting, chats (CLI, Desktop, messaging gateway) keep waiting with no total limit (each key's rest capped by max_hold_seconds) and cron runs give up after 300 s with the provider's refusal unless max_total_wait_seconds is set.

Models

← Back to the catalog · catalog built Oct 8, 2026