909 plugins from the official Hermes plugin catalog: 20 official, 9 verified and 880 from the community. 206 were added in the last week. Search, filter by what you want to do, and copy the install command.
109 plugins. Sorted by HermesWatcher's picks: usefulness, polish and trust. Official: made by Nous Research. Verified: listed with a verified maintainer. Community: built by others, so read the source first.
Ppq
Community
PayPerQ (ppq.ai) OpenAI-compatible model provider for Hermes — per-response cost estimation from ppq's published rate card, chat model discovery from GET /v1/models, automatic per-request Zero Data Retention opt-in…
PayPerQ (ppq.ai) OpenAI-compatible model provider for Hermes — per-response cost estimation from ppq's published rate card, chat model discovery from GET /v1/models, automatic per-request Zero Data Retention opt-in, and a 3-layer picker pin strategy (user-local pins file → live top chat models from ppq's public stats dashboard → generic static fallback; generic installs never get the author's personal pins).
Good to know before installing
Model provider; PPQ_API_KEY and all prompts, tool schemas and responses go to ppq.ai (PayPerQ; terms https://ppq.ai/terms, contact matt@ppq.ai), a relay that routes requests to third-party inference partners, some outside the user's jurisdiction, and frontier providers still see prompts; usage is billed per request from the user's prepaid PayPerQ balance (funded by card or cryptocurrency on ppq.ai; the plugin itself makes no payments). Privacy protections are opt-in per request: for models badged privacyLevel 'zdr' the plugin automatically sends provider={"zdr": true, "data_collection": "deny"} so requests route only to endpoints with a Zero Data Retention policy that do not collect data (the zdr model set refreshes hourly from an unauthenticated GET /v1/models with a pinned fallback); models badged 'e2e' run inside TEE enclaves with no opt-in flag needed — enclave coverage applies to chat by default, not to image/video/audio, and true end-to-end encryption is only available via the optional local ppq-privacy-verifier proxy. Building the model picker, for any provider, starts a background unauthenticated POST to stats.ppq.ai at most hourly to fetch the top chat models; cost estimat
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs PPQ_API_KEY), then asks whether to turn it on.
hermes plugins install ppq
Said no? Turn it on later:
hermes plugins enable ppq
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Copy provider API keys (and provider base-URL overrides) from one profile onto other profiles — a one-time, explicit copy from a desktop page. Per-profile missing/present badges, fill-missing by default with an explicit overwrite opt-in. OAuth sign-ins and messaging bot tokens never travel; values never cross back in responses.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install provider-copy
Said no? Turn it on later:
hermes plugins enable provider-copy
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
RuAPI
Community
RuAPI as Hermes model providers on one key: `ruapi` serves Claude models over RuAPI's native Anthropic Messages API (so Hermes' Anthropic prompt caching and thinking apply), and `ruapi-openai` serves GPT, Gemini…
RuAPI as Hermes model providers on one key: `ruapi` serves Claude models over RuAPI's native Anthropic Messages API (so Hermes' Anthropic prompt caching and thinking apply), and `ruapi-openai` serves GPT, Gemini, DeepSeek, GLM, Qwen, Kimi and other chat models over its OpenAI-compatible API. Each /model picker lists that side's chat models from the account's GET /v1/models list, leaving out image and video models, and context windows and image input are declared for the main models. Maintained by RuAPI.
Good to know before installing
Registers two model providers at import and nothing else (no tools, hooks, commands or threads). Prompts, tool schemas and RUAPI_API_KEY go to https://www.ruapi.ai (/v1/messages and /v1/chat/completions) through Hermes' own clients, and RuAPI forwards each request to the upstream vendor serving the model. The model list is Hermes' standard GET https://www.ruapi.ai/v1/models request with the key; the plugin makes no network requests of its own, adds no headers, sends no telemetry, reads or writes no files and stores no credentials.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs RUAPI_API_KEY), then asks whether to turn it on.
hermes plugins install ruapi
Said no? Turn it on later:
hermes plugins enable ruapi
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
TeamoRouter
Community
TeamoRouter as Hermes model providers on one key: `teamorouter` serves Claude models over TeamoRouter's native Anthropic Messages API (so Hermes' Anthropic prompt caching and thinking apply), and `teamorouter-openai`…
TeamoRouter as Hermes model providers on one key: `teamorouter` serves Claude models over TeamoRouter's native Anthropic Messages API (so Hermes' Anthropic prompt caching and thinking apply), and `teamorouter-openai` serves GPT, Gemini, DeepSeek, GLM and Grok models over its OpenAI-compatible API. Each /model picker lists that side's tool-capable chat models from TeamoRouter's public catalog, leaving out image, service-tier and free-tier variants, and context windows come from the same catalog. Maintained by TeamoRouter.
Good to know before installing
Registers two model providers at import and nothing else (no tools, hooks, commands or threads). Prompts, tool schemas and TEAMOROUTER_API_KEY go to https://api.teamorouter.com (/v1/messages and /v1/chat/completions) through Hermes' own clients, and TeamoRouter forwards each request to the upstream vendor serving the model. The plugin's own request is GET https://api.teamorouter.com/v1/models/pricing, a public endpoint, sent without the key and cached for an hour. `teamorouter-openai` requests carry a fixed `X-Client-Source: hermes-teamorouter-plugin` header (via the profile's default_headers), used only to count traffic from this plugin; Claude requests carry no header from the plugin. No telemetry, no files read or written, no stored credentials, no processes.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs TEAMOROUTER_API_KEY), then asks whether to turn it on.
hermes plugins install teamorouter
Said no? Turn it on later:
hermes plugins enable teamorouter
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Web Deepseek
Community
DeepSeek Search + Fetch — routes web_search and web_extract through DeepSeek's in-house AI search engine and server-side fetcher on api.deepseek.com (opened up in the vendor's 2026-10-17 changelog: AI-native engine…
DeepSeek Search + Fetch — routes web_search and web_extract through DeepSeek's in-house AI search engine and server-side fetcher on api.deepseek.com (opened up in the vendor's 2026-10-17 changelog: AI-native engine indexing hundreds of billions of pages, multilingual, filters SEO spam / GEO manipulation / low-quality AIGC). Registers the provider id `deepseek-web`.
Good to know before installing
Each search/fetch is a separate billed DeepSeek call at $0.75 per 1,000 successful requests per endpoint, and only HTTP 200 responses that produce a result are billable (5 QPS per account per endpoint, plus a per-domain QPS limit on fetch); the provider reuses DEEPSEEK_API_KEY and sends it only to api.deepseek.com; extract returns Markdown only (no HTML variant, so web_extract(format="html") gets Markdown), and anti-bot or JS-rendered sites fail (zhihu.com, x.com, nytimes.com returned HTTP 404 in testing) while static pages work.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs DEEPSEEK_API_KEY), then asks whether to turn it on.
hermes plugins install web-deepseek
Said no? Turn it on later:
hermes plugins enable web-deepseek
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
AIHubMix — unified OpenAI-compatible access to 400+ models; /model picker filtered to tool-capable routes.
How to install
Install it. Hermes asks for any API keys it needs (this one needs AIHUBMIX_API_KEY), then asks whether to turn it on.
hermes plugins install aihubmix
Said no? Turn it on later:
hermes plugins enable aihubmix
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Your AI subscriptions and token usage in Hermes Desktop. A page with Overview, Usage and Plans tabs, plus a status-bar chip where you pick which subscriptions to keep. Quota comes from Hermes's own model.options and usage.bars RPCs; the page polls Hermes' cached windows (Hermes refreshes them in its own background threads) and only its Refresh button asks for an explicit refresh; token usage covers Hermes, Claude Code and the Grok CLI, clicking a day shows that day's per-source, per-model and hourly breakdown, and measured tokens per second are shown per model, per day and overall.
Good to know before installing
Read-only reads outside the plugin's data - Hermes state.db and models_dev_cache.json, ~/.claude/projects/**/*.jsonl and ~/.grok/logs/unified.jsonl plus ~/.grok/sessions/*/*/summary.json (token counts only). No credential, .env or auth.json reads, no network calls, no shell commands, no background processes, no telemetry.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install ai-subscriptions
Said no? Turn it on later:
hermes plugins enable ai-subscriptions
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
AI Stupid Level
Community
AI Stupid Level Smart Router — OpenAI-compatible; routing modes such as auto-tooling send each request to the model currently scoring best on continuously re-run benchmarks, called with your own provider keys.
AI Stupid Level Smart Router — OpenAI-compatible; routing modes such as auto-tooling send each request to the model currently scoring best on continuously re-run benchmarks, called with your own provider keys.
Good to know before installing
Sends your prompts, tool definitions, tool results and ASL_ROUTER_KEY to aistupidlevel.info (S.C. Studio Platforms S.R.L.), which forwards each request to the AI provider it routes to using the provider keys you store on your AI Stupid Level account; model usage is billed to your provider accounts, and prompts are logged only if you enable logging for a key.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs ASL_ROUTER_KEY), then asks whether to turn it on.
hermes plugins install aistupidlevel
Said no? Turn it on later:
hermes plugins enable aistupidlevel
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
AtmoRouter
Community
AtmoRouter — OpenAI-compatible gateway; one key for Claude, GPT, Gemini, GLM, Kimi, Qwen, DeepSeek, MiniMax and Grok models, with the /model picker fed by the live GET /v1/models catalog.
AtmoRouter — OpenAI-compatible gateway; one key for Claude, GPT, Gemini, GLM, Kimi, Qwen, DeepSeek, MiniMax and Grok models, with the /model picker fed by the live GET /v1/models catalog.
Good to know before installing
Sends your prompts, conversation history, tool definitions, tool results and ATMOROUTER_API_KEY to atmorouter.dev, which forwards each request to the upstream infrastructure serving the chosen model; that infrastructure's location and retention vary per model and zero retention is not promised (AtmoRouter states it keeps metadata, not prompt or response content, in its usage records and does not train on API content; https://atmorouter.dev/privacy). Usage is billed per token from a prepaid AtmoRouter balance (USDC on Solana or QRIS); prices vary by capacity tier and a request can route to any listed tier, including tiers above official pricing, unless you set maximum prices under Budgets; failed upstream requests are not billed and the plugin itself makes no payments.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs ATMOROUTER_API_KEY), then asks whether to turn it on.
hermes plugins install atmorouter
Said no? Turn it on later:
hermes plugins enable atmorouter
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Chutes model provider for Hermes Agent via API key.
Good to know before installing
Model provider; prompts, tool schemas and CHUTES_API_KEY go to llm.chutes.ai (or CHUTES_BASE_URL), plus a GET /models catalog probe with the same key
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs CHUTES_API_KEY), then asks whether to turn it on.
hermes plugins install chutes-provider
Said no? Turn it on later:
hermes plugins enable chutes-provider
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
xAI Grok subscription as a Hermes model provider, driven over ACP stdio.
Good to know before installing
Spawns the vendor grok CLI found on PATH (grok agent over ACP stdio, plus grok models / grok login during setup) and drives your existing Grok subscription login; no API key is stored and Hermes provider secrets are stripped from the child environment.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install grok-acp
Said no? Turn it on later:
hermes plugins enable grok-acp
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Hermes Subscription Meter
Community
Provider-neutral subscription quota matrix panel — each provider's subscription window as a single time x quota row (elapsed vs remaining at a glance), with UI-side show/hide per provider row.
Provider-neutral subscription quota matrix panel — each provider's subscription window as a single time x quota row (elapsed vs remaining at a glance), with UI-side show/hide per provider row.
Good to know before installing
Reads provider keys from the current profile's .env and token presence from its auth.json, and calls each provider's own usage/balance API with that key (Kimi, GLM, MiniMax, Command Code, DeepSeek, xAI management, OpenRouter, Alibaba Cloud BSS, Grok, Codex via Hermes); an optional shared_sources setting reads another profile's .env/auth.json the same way; the token-activity heatmap reads per-day token totals, providers and model names from the state.db of this profile and of every other profile on the install (read-only, no message content, nothing leaves the machine); nothing is written outside this plugin's settings.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install hermes-subscription-meter
Said no? Turn it on later:
hermes plugins enable hermes-subscription-meter
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Kiro CLI (AWS) as a Hermes model provider, driven over ACP stdio.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install kiro-acp
Said no? Turn it on later:
hermes plugins enable kiro-acp
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Lightningai
Community
Lightning AI as a Hermes model provider (--provider lightning, lightning-ai, lightningai): OpenAI-compatible gateway at https://lightning.ai/api/v1, models fetched live from /models.
Lightning AI as a Hermes model provider (--provider lightning, lightning-ai, lightningai): OpenAI-compatible gateway at https://lightning.ai/api/v1, models fetched live from /models.
Good to know before installing
Registers one model provider at import and nothing else (no tools, hooks, commands or threads); chat requests and the model list go to lightning.ai through Hermes' own client with LIGHTNING_API_KEY (or LIGHTNING_AI_API_KEY), optional LIGHTNING_BASE_URL overrides the endpoint; the plugin itself opens no connections, reads/writes no files and starts no processes.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs LIGHTNING_API_KEY), then asks whether to turn it on.
hermes plugins install lightningai
Said no? Turn it on later:
hermes plugins enable lightningai
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Prism OpenAI-compatible inference with long-context DeepSeek models.
How to install
Install it. Hermes asks for any API keys it needs (this one needs PRISM_API_KEY), then asks whether to turn it on.
hermes plugins install prism
Said no? Turn it on later:
hermes plugins enable prism
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Gondola, a USDC-settled marketplace API for Venice AI inference
How to install
Install it. Hermes asks for any API keys it needs (this one needs GONDOLA_API_KEY), then asks whether to turn it on.
hermes plugins install gondola-provider
Said no? Turn it on later:
hermes plugins enable gondola-provider
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
AnyRouter — unified model gateway (OpenAI-compatible); /model picker filtered to tool-capable routes, first-party meta-models like anyrouter/hermes.
Good to know before installing
Sends your prompts and ANYROUTER_API_KEY to anyrouter.dev, a third-party relay that forwards to upstream vendors (OpenAI, Anthropic, Google, xAI, …), on some plans through a shared pool of other members' donated free-tier vendor keys; billed in prepaid AnyRouter credits. anyrouter/hermes is AnyRouter's own routing meta-model, not a Nous Research model. Opt-in ANYROUTER_APP_ATTRIBUTION=1 adds Hermes attribution headers.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs ANYROUTER_API_KEY), then asks whether to turn it on.
hermes plugins install anyrouter
Said no? Turn it on later:
hermes plugins enable anyrouter
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Experiential Labs - OpenAI-compatible multi-model gateway provider (chat, /model picker, aux and curated fallback models, /usage wallet snapshot). All network calls go to api.experientiallabs.ai - /v1 chat + models via Hermes' own transport, /api/v1/credits and /api/v1/key only when /usage runs; no telemetry; credentials resolve through Hermes routes (hermes auth / .env).
Good to know before installing
When you pick Experiential Labs as your model, every prompt, tool result and attachment of that session goes to api.experientiallabs.ai, a third-party gateway that routes to upstream model vendors. /usage sends your key to its Cost API (GET /credits and /key) or to the cost_api_base you set. Independent integration, not affiliated with Experiential Labs.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs EXPLABS_API_KEY), then asks whether to turn it on.
hermes plugins install hermes-experientiallabs
Said no? Turn it on later:
hermes plugins enable hermes-experientiallabs
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Delegate-only, fail-closed Kimi Code ACP integration for Hermes Agent
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install kimi-code-delegate
Said no? Turn it on later:
hermes plugins enable kimi-code-delegate
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Tsubasa OpenAI-compatible model provider (tool calling not supported yet).
Good to know before installing
Sends prompts and your TSUBASA_API_KEY to api.tsubasa.sh, operated by PalmAndWand; the API currently serves Canada only and answers HTTP 451 to requests from elsewhere.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs TSUBASA_API_KEY), then asks whether to turn it on.
hermes plugins install tsubasa
Said no? Turn it on later:
hermes plugins enable tsubasa
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Usage Flame
Community
Pinned glowing chip + fire-themed panel with live subscription-quota windows (remaining %, reset countdown, burn-rate pace and run-out forecast with sparkline history) for every provider Hermes reports usage for.
Pinned glowing chip + fire-themed panel with live subscription-quota windows (remaining %, reset countdown, burn-rate pace and run-out forecast with sparkline history) for every provider Hermes reports usage for. 12 color themes and fonts, RU/EN, zero dependencies, works on Windows.
Good to know before installing
Runs hermes usage --json through the Desktop gateway (cli.exec) every 1–15 minutes and sweeps up to 8 providers every 15 minutes; each run queries that provider's usage endpoint with the credential Hermes already holds. Reads the composer's selected provider from Desktop localStorage. No network calls of its own.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install usage-flame
Said no? Turn it on later:
hermes plugins enable usage-flame
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Yolo-Auto: flat-rate OpenAI-compatible API with plan-filtered live model discovery.
How to install
Install it. Hermes asks for any API keys it needs (this one needs YOLO_AUTO_API_KEY, YOLO_AUTO_BASE_URL), then asks whether to turn it on.
hermes plugins install yolo-auto
Said no? Turn it on later:
hermes plugins enable yolo-auto
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Ai Usage Tracker
Community
Live subscription-quota windows for every AI provider Hermes can route to, as a desktop page plus a status-bar chip, with a per-profile picker — Codex, Claude, Copilot, OpenCode Go/Zen, Z.AI, Kimi, MiniMax, Nous…
Live subscription-quota windows for every AI provider Hermes can route to, as a desktop page plus a status-bar chip, with a per-profile picker — Codex, Claude, Copilot, OpenCode Go/Zen, Z.AI, Kimi, MiniMax, Nous, OpenRouter, DeepSeek.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install ai-usage-tracker
Said no? Turn it on later:
hermes plugins enable ai-usage-tracker
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Next Steps
Community
Next-step suggestions under the Hermes Desktop composer after each turn: local Ollama inference, per-session state, target routing (session, new tab, bots, kanban), tiny-model capacity profiles, EN/DE UI.
Next-step suggestions under the Hermes Desktop composer after each turn: local Ollama inference, per-session state, target routing (session, new tab, bots, kanban), tiny-model capacity profiles, EN/DE UI. No API keys.
Good to know before installing
After every agent turn, sends the last 8 messages (each cut to 200 chars) plus the working directory to Ollama on localhost; clicking a suggestion immediately submits it as a prompt in the current session, a new session, or another profile's session, or creates a kanban card, and for non-current targets also attaches the working directory and the last 6 messages (on by default, can be turned off under Targets).
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install next-steps
Said no? Turn it on later:
hermes plugins enable next-steps
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Lightningai Rate Limit
Community
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.
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.
Good to know before installing
Registers one llm_execution middleware and nothing else; no network calls, files, or processes of its own.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install lightningai-rate-limit
Said no? Turn it on later:
hermes plugins enable lightningai-rate-limit
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
JetBrains Junie coding agent as a Hermes model provider over ACP.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install junie-acp
Said no? Turn it on later:
hermes plugins enable junie-acp
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Choose a separate scorer to set the reasoning effort of each Hermes request.
Good to know before installing
Off by default; when a mode is enabled (or on an explicit `/hae probe`), sends the latest user message (or the parent-written subagent goal), truncated to 4000 characters, plus any configured guidance to the scorer you select (TypeSafe Jev at api.typesafe.ai by default, or OpenAI Decisions, OpenRouter, Cloudflare Workers AI, Nace at console.nace.ai, or a custom URL) using that service's key; opt-in settings can also send the target model identity, up to 6 earlier user/assistant text messages (1200 characters each) and a separate continuation question to the same scorer; in Hermes Desktop it also sets the focused chat's session reasoning selector through the gateway `config.set` API after each applied change, and it keeps a prompt-free effort-change history (64 changes × 64 conversations), per-conversation mode overrides (at most 256 conversations) and per-route cache verdicts built from provider token counters (at most 128 routes) in its plugin data directory.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install hermes-adaptive-effort
Said no? Turn it on later:
hermes plugins enable hermes-adaptive-effort
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
TypeSafe's Jev decision model as Hermes' smart-approval reviewer only: it cannot generate text and refuses every other task. Supports TypeSafe direct, OpenRouter, and configurable Jev-compatible HTTPS endpoints with optional endpoint-specific authentication; validates typed answers and endpoint/redirect boundaries, redacts command credentials, and records bounded structured audit logs.
Good to know before installing
Each command routed to smart approval (redacted best-effort) and the operator's smart-policy text leave the machine for the configured third-party endpoint; provider or validation failures fail closed to ESCALATE.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs TYPESAFE_API_KEY), then asks whether to turn it on.
hermes plugins install jev-approvals
Said no? Turn it on later:
hermes plugins enable jev-approvals
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Kfchow Llm Value Router
Community
Per-turn LLM routing: on each matching turn a TypeSafe Jev classifier call (api.typesafe.ai) receives turn-shape features plus the first 1200 chars of the last user message (shadow mode included) and labels it…
Per-turn LLM routing: on each matching turn a TypeSafe Jev classifier call (api.typesafe.ai) receives turn-shape features plus the first 1200 chars of the last user message (shadow mode included) and labels it free/paid; high-confidence routine turns are downgraded to the provider's configured free rung, strategic mid-rung turns on Nous are escalated to the configured premium rung after a 2-token billed credit probe (Nous only, fail-closed). Fail-open, shadow-by-default, per-provider rungs from the user's lane2_config.json (leaderboard resolver script optional). Probe model id is fixed in code (z-ai/glm-5.3-flash).
Good to know before installing
Once you list models in ~/.hermes/jev/lane2_config.json, the first call of each matching turn sends message/tool counts and the first 1,200 characters of the last user message (send_excerpt, on by default) to TypeSafe Jev at api.typesafe.ai with your JEVI_API_KEY, in shadow mode as well as live; in live mode Jev's answer switches the request (and every later call of that turn, via an llm_execution wrapper) to the free, flash or premium model you configured on the same provider; with escalation set up on Nous it sends a 2-token billed ping to the Nous inference API with NOUS_API_KEY at most every 5 minutes; every turn appends a decision row (with that excerpt on routed turns) to ~/.hermes/jev/lane2-live.jsonl, which is never rotated.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install kfchow-llm-value-router
Said no? Turn it on later:
hermes plugins enable kfchow-llm-value-router
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Hermes Model Switcher
Community
Choose models across Hermes profiles from a Dashboard tab: a per-profile picker built on host-supplied model data (SDK-authenticated GET /api/model/options), a preview of provider/model intent across every supported…
Choose models across Hermes profiles from a Dashboard tab: a per-profile picker built on host-supplied model data (SDK-authenticated GET /api/model/options), a preview of provider/model intent across every supported model-selection slot (main, delegation, auxiliary, judge, fallback, MoA, cron, plugin and specialist), and one-click apply or revert with presets. Main-slot preview shows intended provider/model, not the exact persisted diff; the exact diff is shown only after host readback.
Good to know before installing
Its apply route reads and edits the profiles' config.yaml (that is the plugin's function) through public seams only: POST /api/model/set for main and compatible auxiliary slots, and public hermes_cli.config load/save under the target home for other slots; credential presence checks use public profile-scoped secret helpers (agent.secret_scope), and profile discovery uses public hermes_constants. The plugin makes no direct third-party requests and opens no provider caches or pricing registries directly, but its browser tab does call the host's /api/model/* routes through the Dashboard SDK, and the host options route may itself initiate provider or pricing I/O even without an explicit refresh request, so reads are not guaranteed cache-only. It runs no shell commands or background processes and reports nothing. The private undo journal stores a full pre-change snapshot of each config it edits, which can contain sensitive fields including embedded credentials. Saved presets also persist reviewed change values, potentially including inline credentials or credential-bearing base URLs, in presets.json (0600) under get_hermes_home()/state/hermes-model-switcher/ (0700). The host write route
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install hermes-model-switcher
Said no? Turn it on later:
hermes plugins enable hermes-model-switcher
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Fleet-wide provider and model presets with CLI and Hermes Desktop support.
Good to know before installing
Writes model/provider keys into the config.yaml of the profiles you select (backup taken first).
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install protean-model-sync
Said no? Turn it on later:
hermes plugins enable protean-model-sync
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Hermes Structured Aux Models
Community
Routes selected Hermes auxiliary tasks (approval, MCP sampling, compression) through bounded Jev decision calls on OpenRouter instead of free-form chat prompts, failing open to the operator's own auxiliary provider for…
Routes selected Hermes auxiliary tasks (approval, MCP sampling, compression) through bounded Jev decision calls on OpenRouter instead of free-form chat prompts, failing open to the operator's own auxiliary provider for anything it cannot express as a decision.
Good to know before installing
Sends redacted approval prompts, MCP tool names and compression transcript blocks to openrouter.ai using your OpenRouter key (read-only); on any error approvals escalate to you, never auto-approve; the default decision_model is a moving alias, pin it.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
LLM Council (karpathy/llm-council) as a Hermes plugin. Four fixed advisor seats (First-Principles Analyst, Skeptic, Pragmatist, Researcher) answer in parallel, anonymously review and rank each other, and a Chairman model synthesizes the final answer. Members borrow your existing provider credentials - no API keys. Registers a Council group in every model menu, a council_deliberate tool, /council, hermes council CLI, and a desktop panel.
Good to know before installing
Council_deliberate and the Council model fan each prompt (as a session model, the whole conversation) out to every seat, judge and chairman model you assign, up to 2N+1 billed calls per turn on your existing provider credentials; it also adds a non-secret "council" marker row to auth.json and keeps run history in $HERMES_HOME/council/runs/.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install hermes-council
Said no? Turn it on later:
hermes plugins enable hermes-council
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Surp Hermes X402 Llm
Community
Marketplace-aware LLM routing for Surp — live prices for all models, provider TPS and trusted flags, mid-chat seller switching, secret masking, and approval-gated paid chat.
Marketplace-aware LLM routing for Surp — live prices for all models, provider TPS and trusted flags, mid-chat seller switching, secret masking, and approval-gated paid chat.
Good to know before installing
The messages passed to surp_chat and SURP_API_KEY go to the surp.ivc.lol gateway, run by the individual developer ivcained (operator page https://surp.ivc.lol/operator, terms https://surp.ivc.lol/terms; not affiliated with Surplus Intelligence), which forwards them to third-party sellers on the Surplus Intelligence marketplace, including sellers not flagged trusted unless trusted_only is set; paid surp_chat calls spend from the user's prepaid Surp balance (USDC on Base, 5 % gateway markup), each behind a per-model Hermes approval prompt (denied in cron and other unattended runs by default) plus a per-request ceiling (max_spend_usd, default $0.05); the price, provider, quote, combo and cache tools call the same gateway without a key; routing preferences are stored under HERMES_HOME/cache/surp-hermes-x402-llm/.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs SURP_API_KEY), then asks whether to turn it on.
hermes plugins install surp-hermes-x402-llm
Said no? Turn it on later:
hermes plugins enable surp-hermes-x402-llm
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
A quotum seat's Venice key as a provider. Private and anonymized models, with the seat's daily cap, spend and the 20:00 UTC bell in /usage, and a Seals tab in hermes dashboard with the seat's record.
Good to know before installing
Prompts and QUOTUM_SEAT_KEY go to api.venice.ai; /usage, Desktop usage and the Seals tab send a 16-hex sha256 handle of the key to quotum.org, then the Seals tab reads the seat's public record from quotum.org (the key itself is never sent there); QUOTUM_X_SEARCH=1 swaps in its own client that drops Hermes web_search for Venice-side web and X search (billed per search); seats are funded by the QUOTUM crypto token
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs QUOTUM_SEAT_KEY), then asks whether to turn it on.
hermes plugins install quotum
Said no? Turn it on later:
hermes plugins enable quotum
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Model Picker
Community
Per-turn cost classifier across three model tiers (Quick / Standard / Expert): rates each user turn from configurable best_for lists and rewrites the outgoing request's model through the llm_request middleware, biased…
Per-turn cost classifier across three model tiers (Quick / Standard / Expert): rates each user turn from configurable best_for lists and rewrites the outgoing request's model through the llm_request middleware, biased to keep the previous tier unless the turn changes shape, with escalate_model for tool failures.
Good to know before installing
The plugin rewrites the model field of every outgoing request for a classified session, picking between three configured model ids that must all belong to the session's own provider (a foreign-provider tier is refused and the session model stands); it makes one bounded auxiliary classifier call through the host's plugin LLM route on each classified turn (up to about 12,000 characters of recent conversation plus the prompt), reading its model ids from config.json next to the plugin, MODEL_PICKER_CONFIG, or MODEL_PICKER_* env, and falls back to the host's primary model; routing decisions, with the first 120 characters of each classified prompt, are logged to $HERMES_HOME/logs/model-picker.log; a classifier-driven tier change can ask the context engine to compact the transcript before the switch, and escalate_model replaces the next request's context with a model-written handoff summary plus the recent tail; that engine registers only when the host config sets context.engine: model-picker.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install model-picker
Said no? Turn it on later:
hermes plugins enable model-picker
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Severian
Community
Local-first long-term memory for Hermes agents: a canonical append-only store (SQLite or PostgreSQL+pgvector) with five-dimensional tenant/profile/collection/agent/session scope, hybrid BM25+vector retrieval…
Local-first long-term memory for Hermes agents: a canonical append-only store (SQLite or PostgreSQL+pgvector) with five-dimensional tenant/profile/collection/agent/session scope, hybrid BM25+vector retrieval with a re-ranker, memories that cite the observations they came from, per-turn user facts, real dates next to relative times, truth resolution when a newer fact replaces an older one, and a conflict note when two returned memories disagree. Fully offline by default; Qwen3-Embedding-0.6B semantic embeddings opt-in, locally or in a user-owned sidecar. On OmniMemEval's public long-term-memory leaderboard (its own models, prompts and full public sets) it scores 90.6 LongMemEval (1st), 87.3 LoCoMo (2nd) and 71.6 BEAM 100K (2nd, within noise of the lead); it re-ran LCM-X to check the board's records, and per-question results, a strict second marker and scripts are published in the repo.
Good to know before installing
Stores every conversation turn in one SQLite database under the Hermes root (`<hermes root>/severian`) shared by all profiles with rows scoped per profile, or in the PostgreSQL database named by `SEVERIAN_DSN`; the opt-in Qwen/Granite embeddings download a model from Hugging Face on first use, and the opt-in embedding sidecar sends memory text to the URL you configure.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs SEVERIAN_DSN), then asks whether to turn it on.
hermes plugins install severian
Said no? Turn it on later:
hermes plugins enable severian
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Guided Aixy inference setup with optional MCP tools: hermes aixy setup selects an available model or route, and hermes aixy mcp connects tools later. MCP is skipped by default.
Good to know before installing
Exposes CLI commands only, with no automatic hooks or runtime tools. Explicit inference setup sends the project key in an authenticated GET /models to the configured Aixy gateway (https://api.aixy-gateway.com/v1 by default), rejects redirects, and asks before updating the selected Hermes profile's provider and main model settings. The key is stored through Hermes' credential writer as AIXY_API_KEY; provider settings contain a variable reference. Model requests send Hermes' opaque conversation scope in X-Aixy-Session-ID for grouping in Aixy Activity. No inference requests are sent during setup. Optional MCP setup starts the installed Hermes CLI as a child process for browser OAuth, credential storage and tool selection against the independent MCP endpoint (https://api.aixy-gateway.com/mcp by default). The child uses the selected profile, disables inherited unattended and YOLO flags, and receives no key in command arguments. Setup requires an interactive terminal. No additional dependencies, telemetry, persistent background processes or self-updater.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install aixy
Said no? Turn it on later:
hermes plugins enable aixy
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
CloudGPU
Community
cloudgpu.app models (DeepSeek, Kimi, GLM, MiniMax) via the OpenAI-compatible API at cloudgpu.app/v1: live model list from the public /v1/models, DeepSeek V4.1 Flash as the default.
cloudgpu.app models (DeepSeek, Kimi, GLM, MiniMax) via the OpenAI-compatible API at cloudgpu.app/v1: live model list from the public /v1/models, DeepSeek V4.1 Flash as the default.
Good to know before installing
Model provider; prompts, tool schemas and CLOUDGPU_API_KEY go to cloudgpu.app (or to CLOUDGPU_BASE_URL when the user sets it).
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs CLOUDGPU_API_KEY), then asks whether to turn it on.
hermes plugins install cloudgpu-provider
Said no? Turn it on later:
hermes plugins enable cloudgpu-provider
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Run Hermes on CoreWeave Serverless Inference with live model discovery, streaming responses, and an OpenAI-compatible API.
Good to know before installing
Hermes sends model discovery and chat requests, including prompts and tool results, to https://api.inference.wandb.ai/v1 (CoreWeave / W&B Inference) using COREWEAVE_API_KEY; the installed provider registers a profile only and reads no credential files, starts no processes and adds no telemetry.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs COREWEAVE_API_KEY), then asks whether to turn it on.
hermes plugins install coreweave
Said no? Turn it on later:
hermes plugins enable coreweave
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
DSers — Multi Platform Dropshipping
Community
DSers multi-platform dropshipping connector for dropshippers: supplier discovery, product sourcing, store management, supplier mapping, order fulfillment, and shipment tracking.
DSers multi-platform dropshipping connector for dropshippers: supplier discovery, product sourcing, store management, supplier mapping, order fulfillment, and shipment tracking. The DSers ecosystem includes AliExpress, Alibaba.com, 1688, DVAN, Shopify, WooCommerce, Wix, eBay, TikTok Shop, Amazon, Walmart, BigCommerce, Squarespace, Square, Ecwid, Magento, SHOPLINE, Jumpseller, Big Cartel, Cartpanda, Genstore, and LPQV; available operations depend on account and channel access.
Good to know before installing
Configuration-only portable MCP connector, with no bundled skills or native tools. Hermes v0.22.5 requires manual native OAuth connection setup. A DSers Advanced, Pro, or Enterprise subscription is required. Tool arguments and results are exchanged with ai.dsers.com; Hermes manages OAuth credentials. Remote tools include write operations, among them supplier-order placement that spends money through the user's DSers account, pricing changes and listing publication; the package and the documented native entry mark the server untrusted so Hermes asks before non-read-only calls, and the remote tool set can change independently of the pinned package. Removing the plugin alone leaves the native MCP connection.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install dsers
Said no? Turn it on later:
hermes plugins enable dsers
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
EU Mode (beta): HaloGuard EU, Astroware's guard API hosted in the EU, checks each message and each reply (allow or block). EU Mode looks for personal data in what users send and masks what it finds before the request reaches the model, then puts the originals back in the reply, on your machine.
Good to know before installing
On every turn the conversation's user and assistant text (not system prompts, tool results, files or images) goes to api.astroware.ai (or the HALOGUARD_BASE_URL you set) with your own HaloGuard EU key, up to twice per turn (your message, then the reply); fail-open: if the API does not answer, the message goes on unchecked and not masked, and the reply says so; reads two Hermes settings (session titles, context compression) only to say when they are on; stores SHA-256 fingerprints of blocked messages, never their text.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs HALOGUARD_API_KEY), then asks whether to turn it on.
hermes plugins install eu-mode
Said no? Turn it on later:
hermes plugins enable eu-mode
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Profile-bound semantic session handoffs for CLI and Desktop with independent destination and optional summary-writer models. Derived from yuzushi-dev/session-handoff.
Good to know before installing
Reads bounded persisted session evidence from the originating profile's state.db and project/Git metadata; runs local Git and foreground Hermes subprocesses without a shell; stores private handoff/journal sidecars under that profile; optional writer and new chat turns use configured model providers and may incur inference costs. No telemetry or plugin-owned credential store. Four internal tool-policy imports remain version-coupled; no runtime overrides or self-updater.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install hermes-handoff
Said no? Turn it on later:
hermes plugins enable hermes-handoff
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Memory provider with keyed corrections you can undo. A correction retires the old value by key, so it stops being recalled, and inspeximus_revert puts the previous value back from the key alone, without anyone retyping what the record used to say. Recall before each turn returns retrieval minus what a later correction retired, so a value corrected three sessions ago cannot come back as context. Adds inspeximus_remember, inspeximus_correct, inspeximus_revert, inspeximus_forget and inspeximus_forget_me.
Good to know before installing
Installs the inspeximus package from PyPI (inspeximus>=3.23.1,<4, including its `inspeximus` command-line tools) into the Hermes environment; the provider makes no network calls and carries no telemetry: memories live in a local JSON file under the profile's Hermes home (or a path you set), recalled memories are added to each turn's context and to the compression summary prompt, and writes made with the built-in memory tool are mirrored into the store.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install inspeximus
Said no? Turn it on later:
hermes plugins enable inspeximus
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Write one namespace in cluster.json to approve the scope, then use four reads: list pods, get one pod, list events, and read logs. Kubernetes is a registered trademark of The Linux Foundation. kubernetes-mcp-server 0.0.68 is the GitHub release binary. The plugin downloads kubernetes-mcp-server-<os>-<arch> from https://github.com/containers/kubernetes-mcp-server/releases/download/v0.0.68/ into the plugin data directory, checks the sha256 against constants taken from that release's GitHub asset digest, and starts that file. MCP initialize and tools/list are answered before that download. A partial download is kept and continued with HTTP Range. A mismatch, including a file that was already there, is refused. read_only is true, toolsets stay core, and only pods_list_in_namespace, pods_get, events_list, and pods_log are enabled. Helm is not offered. Secret, ConfigMap, and ServiceAccount are denied. configuration_view is not listed. prod, production, live, and prd names are refused unless allow_production is true. Public and link-local hosts are always refused. The host must be local, and DNS is not resolved. readOnlyHint is true, so no approval card is shown. Before the call, name the namespace, the object, and that it only reads, because status, events, and logs reach the model. This plugin does not create a cron job.
Good to know before installing
Reads the kubeconfig you name in cluster.json (read-only) and sends its token only to that kubeconfig's API host (plain http sends it unencrypted); on the first tool call downloads the kubernetes-mcp-server 0.0.68 GitHub release binary (~90 MB) into the plugin data directory, refuses it unless its sha256 matches the pinned release digest, and runs it as a subprocess (a file swap between the check and the start is not fully excluded); pod status, events and logs reach the model, with password-like env values and last-applied-configuration redacted; no HTTP proxy is used; gateway users can call these read tools with that kubeconfig; stop with hermes plugins disable kubernetes or hermes tools disable mcp-kubernetes.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install kubernetes
Said no? Turn it on later:
hermes plugins enable kubernetes
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Modular Cloud model-provider plugin — OpenAI-compatible API for open models (MiniMax, DeepSeek, Gemma), with per-model reasoning controls.
How to install
Install it. Hermes asks for any API keys it needs (this one needs MODULAR_API_KEY), then asks whether to turn it on.
hermes plugins install modular
Said no? Turn it on later:
hermes plugins enable modular
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Obscurify.ai
Community
Obscurify.ai as a Hermes model provider (`--provider obscurify`, or Obscurify.ai in `hermes model`): a privacy-focused, OpenAI-compatible API to 200+ models with zero-data-retention routes and account-number…
Obscurify.ai as a Hermes model provider (`--provider obscurify`, or Obscurify.ai in `hermes model`): a privacy-focused, OpenAI-compatible API to 200+ models with zero-data-retention routes and account-number sign-up (no email). The model list leaves out decision models and models under Hermes' 64K context minimum, context windows come from the catalog, and reasoning effort is sent as `reasoning_effort`.
Good to know before installing
Registers one model provider at import and nothing else (no tools, hooks, commands or threads); chat requests go to https://obscurify.ai/v1 through Hermes' own client with OBSCURIFY_API_KEY, which Hermes reads; the plugin itself only fetches the public model catalog (GET https://obscurify.ai/v1/models, no credentials) at most once an hour per process, reads and writes no files and starts no processes. Usage is billed from the user's prepaid Obscurify.ai balance; the plugin makes no payments.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs OBSCURIFY_API_KEY), then asks whether to turn it on.
hermes plugins install obscurify-provider
Said no? Turn it on later:
hermes plugins enable obscurify-provider
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Real OpenCode CLI over ACP as a Hermes model provider, with curated free-model selection and Hermes-owned tool execution and approvals. Independent stdlib transport using only the documented provider API, not an HTTP compatibility client or a handoff to OpenCode's autonomous tools.
Good to know before installing
Starts the separately installed opencode acp executable for discovery/inference in the included restricted workspace; forwards the conversation, tool schemas and results to OpenCode and its selected upstream model. The CLI uses its normal HOME/configuration/login and may load user-configured vendor plugins/hooks; its normal network calls, local records and vendor terms apply. Child environment is allowlisted; Hermes/provider keys and YOLO settings are not inherited. Plugin code reads no credential stores, writes no runtime state, makes no direct network calls, installs no binaries and sends no telemetry. Native ACP permission/file/terminal requests are refused, native tool events abort the request, and selection must be confirmed before inference. This is not an OS sandbox or an authorization to use OpenCode; broader vendor policies can override workspace restrictions, and free availability/pricing/privacy can change.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install opencode-free-acp
Said no? Turn it on later:
hermes plugins enable opencode-free-acp
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Uuid Ref
Community
@uuid: context references that decode a UUID or ULID for the model: @uuid:<id> takes a UUID in any common spelling (hyphens or not, braces, upper case, urn:uuid:) or a ULID, and attaches what its bits say, read…
@uuid: context references that decode a UUID or ULID for the model: @uuid:<id> takes a UUID in any common spelling (hyphens or not, braces, upper case, urn:uuid:) or a ULID, and attaches what its bits say, read the way RFC 9562 lays them out: version and variant in words, the creation time a v1, v6, v7 or ULID carries in UTC with how long ago, the clock sequence and node of a v1 or v6 and whether the node is random or looks like a network card (MAC) address, the local id and domain of a v2, a ULID's 128 bits written as a UUID, and the Nil, Max and RFC namespace UUIDs by name; up to 10 identifiers in one reference are compared by creation time; the TUI and Desktop composer preview an identifier as you type it.
Good to know before installing
Reads only the text of the reference itself and the system clock, using Python's re, datetime and fractions; nothing is looked up; no network, no files read or written, no subprocess, no credentials read; the plugin keeps no copy of the identifiers, but the @uuid: reference and the decoded text become part of the message sent to your model provider and saved in the session history; register() only adds the @uuid: reference provider.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install uuid-ref
Said no? Turn it on later:
hermes plugins enable uuid-ref
Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide↗ (opens in a new tab).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
No plugins match that search.
Read before you install
Plugins run code inside your agent. Official plugins come from Nous Research's own repo. Community plugins are independent projects, so check the source, the permissions they ask for and any API keys they need. New to plugins? Start with skills vs plugins vs MCP.
