All plugins

munito-provider

Munito AI model providers: open models (GLM-5.3-Flash, DeepSeek-V4-Flash, DeepSeek-V4.1-Flash, Qwen3.8-27B, Kolibri 1) on a global host and an EU-only host, with the context window, image input and price of each model bundled. Disclosure: registers two model providers at import and nothing else (no tools, hooks, commands or threads); requests go to https://api.munito.ai/inference/v1 or https://api.eu.munito.ai/inference/v1 through Hermes' own client with MUNITO_API_KEY, which Hermes reads; the plugin itself opens no connections, reads and writes no files, starts no processes and sends no telemetry.

munitoaiModelsv0.1.0Updated 5 days ago

About

Munito AI model providers: open models (GLM-5.3-Flash, DeepSeek-V4-Flash, DeepSeek-V4.1-Flash, Qwen3.8-27B, Kolibri 1) on a global host and an EU-only host, with the context window, image input and price of each model bundled. Disclosure: registers two model providers at import and nothing else (no tools, hooks, commands or threads); requests go to https://api.munito.ai/inference/v1 or https://api.eu.munito.ai/inference/v1 through Hermes' own client with MUNITO_API_KEY, which Hermes reads; the plugin itself opens no connections, reads and writes no files, starts no processes and sends no telemetry.

Munito AI for Hermes Agent

This plugin makes Munito AI a model provider of Hermes Agent.
Munito AI serves open models for Europe, private by default, on an OpenAI-compatible API.

Install

hermes plugins install munitoai/hermes-provider

Create an API key at console.munito.ai/keys, and put it in ~/.hermes/.env:

MUNITO_API_KEY=munitoai_...

Then run hermes model and pick Munito AI, or run hermes --provider munito.

Providers

ProviderHostUse it when
munito (Munito AI)https://api.munito.ai/inference/v1Any region can process the request.
munito-eu (Munito AI (EU))https://api.eu.munito.ai/inference/v1Each request must stay in the EU.

Both use the same key.

Models

ModelContextInput
zai-org/glm-5.3-flash1,048,576Text, images
deepseek-ai/deepseek-v4-flash1,048,576Text
deepseek-ai/deepseek-v4.1-flash-10171,048,576Text, images
qwen/qwen3.8-27b262,144Text, images
aleph-alpha/kolibri-11,048,576Text

The prices are at docs.munito.ai/models.

Reasoning

The plugin sends the effort of Hermes as reasoning_effort. Munito AI moves each level to the nearest level that the model has.
When you turn reasoning off, the plugin sends none: the model stops its reasoning, and a model that always reasons, such as GLM-5.3-Flash, runs its lowest level.
See Reasoning models.

What the plugin does

The plugin registers two model providers at import, and nothing else.
Hermes sends the chat requests and the model list request to the host of the provider, with MUNITO_API_KEY, through its own client.
Hermes also sends a prompt_cache_key, which keeps a conversation on its prompt cache.
Hermes shows the cost of each response at the posted prices of models.json. A price rule of your organization can lower the price that you pay.

What it reaches

  • Network: only the host of the provider that you choose, api.munito.ai or api.eu.munito.ai. Hermes sends each request through its own client.
  • Credentials: only MUNITO_API_KEY, which Hermes reads from the active profile. The plugin reads no file and stores nothing.
  • No telemetry, no shell commands, no background process, and no self-update.

License

MIT

README from the reviewed commit 81b6b62; it updates when the author re-pins.

Developer Mode

Explore built-in Hermes toolsets and actions.

HermesAgent

Developer?

Create a Hermes extension for Desktop or agent workflows.

Developer Section