Skip to content

The agent that grows with you

plugin-catalog: add token-rate and catalogo-it (community; both from the Italian language-pack repo)

Lazzdaycod839ccd22b206
diff --git a/plugin-catalog/catalogo-it.yaml b/plugin-catalog/catalogo-it.yaml
new file mode 100644
index 00000000000..106dec53928
--- /dev/null
+++ b/plugin-catalog/catalogo-it.yaml
@@ -0,0 +1,31 @@
+name: catalogo-it
+repo: https://github.com/Lazzdaycod/hermes-lang-it
+sha: 7bb28ed61954004053232e9532e659173343a78d
+subdir: plugins/catalogo-it
+title: Plugin Catalog (Italian)
+description: >-
+ The official Hermes plugin catalog in a native page (sidebar entry, route
+ /catalogo, plus a command-palette entry) with an Italian interface and
+ on-the-fly Italian descriptions: Google Translate first, MyMemory as a second
+ public source, and a final fallback to the user's own local llama.cpp model.
+ Disclosure — it fetches the public catalog feed
+ (hermes-agent.nousresearch.com), translate.googleapis.com and
+ api.mymemory.translated.net, and sends the plugin description to the local
+ model endpoint only as the last fallback. That endpoint and its key come from
+ Hermes' own config (model.base_url) and from the key Hermes generated for the
+ local server ($HERMES_HOME/runtimes/llamacpp/.api_key), read through the
+ plugin's own backend route; no credential is stored or sent anywhere else.
+ Translation runs when a plugin entry is opened, not for the whole catalog.
+ No telemetry. UI is Italian-first with an English bundle.
+maintainer: Lazzdaycod
+tier: community
+category: desktop
+requires_hermes: ">=0.21.6"
+docs_url: https://github.com/Lazzdaycod/hermes-lang-it/tree/main/plugins/catalogo-it
+version: "1.0.0"
+platforms: []
+capabilities:
+ provides_tools: []
+ provides_hooks: []
+ provides_middleware: []
+ requires_env: []
diff --git a/plugin-catalog/token-rate.yaml b/plugin-catalog/token-rate.yaml
new file mode 100644
index 00000000000..d70b67b10ae
--- /dev/null
+++ b/plugin-catalog/token-rate.yaml
@@ -0,0 +1,30 @@
+name: token-rate
+repo: https://github.com/Lazzdaycod/hermes-lang-it
+sha: 7bb28ed61954004053232e9532e659173343a78d
+subdir: plugins/token-rate
+title: Token Rate Monitor
+description: >-
+ Live output/input tokens-per-second chip in the Hermes Desktop status bar for a
+ local llama.cpp server. Hermes itself reads the server's log
+ ($HERMES_HOME/logs/llama-server.log, last 200 lines: `tg = X t/s` for output and
+ `prompt eval time ... X tokens per second` for input) and serves it at
+ /api/plugins/token-rate/; the chip polls that route once a second. The counter
+ starts off — click the chip, or run the palette entry "Token Rate: start/stop
+ the tok/s counter" (Ctrl/Cmd+K), to start it; the on/off flag is a file
+ ($HERMES_HOME/cache/token-rate-state.json). It also registers the
+ get_token_rate agent tool, so the model can read its own speed. Disclosure —
+ it reads one local file (the llama.cpp log) and nothing else: no network calls,
+ no external process, no extra port, no API key, no credentials, no telemetry.
+ UI is English by default, Italian when the app locale is Italian.
+maintainer: Lazzdaycod
+tier: community
+category: desktop
+requires_hermes: ">=0.21.6"
+docs_url: https://github.com/Lazzdaycod/hermes-lang-it/tree/main/plugins/token-rate
+version: "2.0.0"
+platforms: []
+capabilities:
+ provides_tools: [get_token_rate]
+ provides_hooks: []
+ provides_middleware: []
+ requires_env: []