All plugins

provider-status

Status-bar quota tracking for 17 providers: Tavily, OpenCode Go, DeepSeek, GLM (z.ai), OpenRouter, Grok (xAI), Codex (OpenAI), OpenAI, Anthropic, Groq, Cerebras, Moonshot Kimi, MiniMax, Google Gemini, Hugging Face, Mistral, and Qwen. DeepSeek and GLM show peak/off-peak gauges and countdowns. Includes OAuth and multi-key pools. This edition does not rotate Hermes environment keys on exhaust, and an expired OAuth token asks for a new login. Codex and Grok checks use their CLI client identity and user-agent. Disclosure — Reads provider API keys from the Hermes .env and its own config.json and calls each enabled provider's own usage or billing endpoint; Codex and Grok sign-ins use those CLIs' OAuth client identity and user-agent, keep the plugin's tokens in its install folder, and ask for a new login on expiry. When the Discord gateway runs, the bot's Discord presence (visible to everyone in servers the bot shares) is updated every 20 seconds by default with tokens/sec, context-window use and the active provider's name with its remaining quota or dollar credit balance (model and running tool are opt-in); turn it off with plugins.entries.provider-status.settings.discord_presence_enabled: false. /pulse and the agent_pulse tool report process-wide telemetry (model, provider, current tool, quota) to anyone allowed to call them on a gateway. Writes a secret-free quota-cache.json into its install folder and reads Hermes config.yaml for the active model.

apoapostolov48Desktopv1.6.8Updated 2 days ago

About

Status-bar quota tracking for 17 providers: Tavily, OpenCode Go, DeepSeek, GLM (z.ai), OpenRouter, Grok (xAI), Codex (OpenAI), OpenAI, Anthropic, Groq, Cerebras, Moonshot Kimi, MiniMax, Google Gemini, Hugging Face, Mistral, and Qwen. DeepSeek and GLM show peak/off-peak gauges and countdowns. Includes OAuth and multi-key pools. This edition does not rotate Hermes environment keys on exhaust, and an expired OAuth token asks for a new login. Codex and Grok checks use their CLI client identity and user-agent. Disclosure — Reads provider API keys from the Hermes .env and its own config.json and calls each enabled provider's own usage or billing endpoint; Codex and Grok sign-ins use those CLIs' OAuth client identity and user-agent, keep the plugin's tokens in its install folder, and ask for a new login on expiry. When the Discord gateway runs, the bot's Discord presence (visible to everyone in servers the bot shares) is updated every 20 seconds by default with tokens/sec, context-window use and the active provider's name with its remaining quota or dollar credit balance (model and running tool are opt-in); turn it off with plugins.entries.provider-status.settings.discord_presence_enabled: false. /pulse and the agent_pulse tool report process-wide telemetry (model, provider, current tool, quota) to anyone allowed to call them on a gateway. Writes a secret-free quota-cache.json into its install folder and reads Hermes config.yaml for the active model.

Screenshot

What You Can Do

  • Read used and remaining quota in the status bar for each enabled provider.
  • Publish this session's tokens/sec, context occupancy, and the backing provider's remaining quota (or credit balance) as the Discord bot presence. /pulse and hermes session-pulse report the same numbers. Disable the standalone discord-presence plugin while this one is publishing so two bots do not fight over the status.
  • When a pet is on screen, one quota line appears in its speech bubble: the active model's remaining balance, or the worst enabled provider if none is active. Near a ceiling it uses a wait tone; at exhaustion it uses an error tone. Turn the bubble off, pick current vs worst, and rewrite the line under Settings → Plugins → Provider Quota Status (the pet settings sit above the Discord ones). Older hosts without the pet door keep the status-bar chips only.
  • Keep multiple accounts per provider and inspect their status.
  • Delete the first key of a provider with the trash glyph on its row. The row goes with its last key.
  • Use an access token that is already configured in the plugin. Expired OAuth tokens require a new login.
  • Provider polling does not read vendor CLI auth files, refresh vendor tokens, write Hermes .env or config.yaml, or copy secrets into a plugin-owned library.env.
  • See DeepSeek's pricing window beside its name, including full-day Chinese public-holiday overrides. The plugin applies official 2025 and 2026 State Council holiday dates; the built-in calendar ends on 2026-12-31.
  • The GLM chip shows its peak/off-peak speedometer even when the quota response omits a weekly window. Z.AI lists Coding Plan peak hours as Monday-Friday 14:00-18:00 Singapore time (UTC+8); off-peak use consumes half the standard credit rate. See Z.AI Coding Plan usage.

Disclosure: quota checks for Codex and Grok use the documented client identity and user-agent expected by their CLI-compatible endpoints. The public edition sends keys only to their own provider endpoints and does not collect telemetry.

Supported providers: Tavily, OpenCode Go, DeepSeek, GLM (z.ai), OpenRouter, Grok (xAI), Codex (OpenAI), OpenAI, Anthropic, Groq, Cerebras, Moonshot Kimi, MiniMax, Google Gemini, Hugging Face, Mistral, and Qwen.

Install

Requires Hermes Agent 0.21.0 or newer.

hermes plugins pack install https://raw.githubusercontent.com/apoapostolov/hermes-agent-awesome-plugins/main/hermes-pack.yaml

Enable Provider Quota Status under Capabilities → Plugins. Open the status-bar gear to configure providers. Never commit real keys.

The public edition keeps quota chips, provider probes, device login, and plugin-owned configuration. It does not perform automatic key rotation into Hermes configuration. An expired OAuth token requires logging in again.

Requirements / Limits

Desktop plus gateway. Quota numbers come from each provider's API. Discord presence uses the Discord platform plugin already in Hermes; it is observer-only. OAuth availability, reset behavior, and account limits follow the provider. This plugin manages configured credentials; it does not remove billing or usage caps.

License

MIT

README from the reviewed commit bdb7434; it updates when the author re-pins.

More by apoapostolov

14 plugins by apoapostolov in the catalog.