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.
909 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.
Adaptive Inference Routing
Community
Opt-in background scheduling for host-known delegated sessions, supported cron execution and explicit worker profiles using an existing Adaptive Inference gateway.
Opt-in background scheduling for host-known delegated sessions, supported cron execution and explicit worker profiles using an existing Adaptive Inference gateway. Interactive and explicitly classified requests retain their routing; model, tools, prompts, output limits and credentials are unchanged.
Good to know before installing
Adds only X-Adaptive-Class on an exactly configured chat-completions endpoint. No network calls, file access, processes, telemetry or credential handling in plugin code. Uses a bounded in-memory session index. Cron detection requires the newer public execution-identity capability; auxiliary routing is an explicit provider configuration, not an auxiliary middleware claim.
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 adaptive-inference-routing
Said no? Turn it on later:
hermes plugins enable adaptive-inference-routing
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.
Identity
Community
View and edit the identity files (SOUL.md, MEMORY.md, USER.md, AGENT.md/HERMES.md) from chat, switch the active profile, and see per-line usage with colour-coded staleness timestamps.
View and edit the identity files (SOUL.md, MEMORY.md, USER.md, AGENT.md/HERMES.md) from chat, switch the active profile, and see per-line usage with colour-coded staleness timestamps. Adds six tools, /identity, /identity-switch and /identity-dashboard commands, and a utilization dashboard pane.
Good to know before installing
Reads and writes the identity files and a line-utilization record inside the selected profile directory under HERMES_HOME, and can change which profile is active; it performs no network I/O and holds no credentials. Disclosure — the model-callable identity_edit tool rewrites SOUL.md/MEMORY.md/USER.md/AGENT.md and identity_switch_profile writes HERMES_HOME/active_profile.
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 identity
Said no? Turn it on later:
hermes plugins enable identity
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).
Give the inference engine behind each request a standard, machine-readable view of the agent session that produced it. Injects an X-Agent-Hint header (base64url JSON: session identity and call index, lifecycle state, soft priority, a cache-pinning hint, optional measured statistics) on main LLM requests, and can emit session lifecycle events out of band as local ndjson or as POSTs to a URL you configure. Request bodies are never modified, and nothing is added or sent until the plugin is enabled. Lets a scheduler pin a session to the instance already holding its KV cache, or rank a user-blocked session above background work, without teaching the engine anything about the client.
Good to know before installing
When enabled, every main LLM request carries an X-Agent-Hint header (base64url JSON with the session id, call index, lifecycle state, priority and cache hints) to whatever provider is configured, not only hint-aware engines; with status_sink: http the same session events and usage/latency statistics are POSTed to the status_url you set, and ndjson writes them under $HERMES_HOME.
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 agent-hint
Said no? Turn it on later:
hermes plugins enable agent-hint
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.
Post Cortex
Community
Self-hosted long-term memory through a post-cortex daemon (https://github.com/julymetodiev/post-cortex): typed records (decisions, fixed problems, code changes) in an entity graph with local semantic search.
Self-hosted long-term memory through a post-cortex daemon (https://github.com/julymetodiev/post-cortex): typed records (decisions, fixed problems, code changes) in an entity graph with local semantic search. Recalls related records from the profile's workspace before each turn, puts the user card and the workspace's project card in the system prompt, mirrors built-in memory writes as records, and adds post_cortex_search, post_cortex_record and post_cortex_context (graph neighbours and reverse dependencies of named components) plus the post-cortex:memory skill. Records and captured turns carry the author hermes:<profile>. Profiles are mapped to shared workspaces by name glob, so a team of profiles recalls each other's records.
Good to know before installing
Talks only to the post-cortex daemon at the configured URL (default http://127.0.0.1:3737; a remote daemon over plain HTTP should sit on a private network or behind TLS): each non-trivial user prompt (up to 2,000 characters) is sent as a search query, and built-in memory writes and post_cortex_record calls are sent as records; with the opt-in capture setting (off by default) each completed turn of the primary agent is sent too: the user's message (with the sender's display name when Hermes knows it), the final reply, tool names and file paths, never tool output; nothing goes to third parties. Disclosure — the daemon stores records (and captured turns, deleted after its message_retention_days) in its own database and redacts credentials, e-mail addresses, phone numbers and public IPv4 addresses on write. Disclosure — PCX_TOKEN (and optionally PCX_URL) is read through the Hermes secret scope; the only local state is $HERMES_HOME/post-cortex.json (0600, never holds the token). No threads or processes of its own (capture runs on Hermes' sync worker), no shell commands, no deletes in post-cortex; cron and subagent runs never write automatically.
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 post-cortex
Said no? Turn it on later:
hermes plugins enable post-cortex
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).
AnyAPI.ai — unified OpenAI-compatible access to 400+ models; /model picker filtered to tool-capable routes.
Good to know before installing
Sends your prompts, tool results and ANYAPI_API_KEY to api.anyapi.ai, a third-party relay (AnyAPI Inc.) that forwards them to the upstream vendor serving the chosen model; billed to your AnyAPI account.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs ANYAPI_API_KEY), then asks whether to turn it on.
hermes plugins install anyapi
Said no? Turn it on later:
hermes plugins enable anyapi
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).
Local-first long-term memory backed by total-agent-memory (TAM) over MCP — saves each completed turn (with a noise filter; TAM's quality gate applies), recalls relevant memories before each turn within a token budget, and adds tam_recall / tam_save tools; optional TAM team server for shared company memory.
Good to know before installing
Local mode starts the separately installed tam binary as a child process per session with an allowlisted environment that carries no credentials: Hermes provider keys (including HF_TOKEN and OLLAMA_API_KEY), TAM_API_TOKEN and any *_TOKEN / *_API_KEY / *_SECRET / *_PASSWORD variable are withheld, and of HF_* / OLLAMA_* only non-secret settings pass (OLLAMA_URL, OLLAMA_EMBED_MODEL, HF_HOME, HF_HUB_OFFLINE); it stores user/assistant turn text plus built-in memory additions (not tool output) in TAM's store, by default outside HERMES_HOME and shared with other agents using TAM; remote mode sends the same text to the user-configured URL with an optional TAM_API_TOKEN bearer token; hermes memory setup tam writes tam.json, TAM_API_TOKEN to .env and memory.provider in config.yaml.
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 tam
Said no? Turn it on later:
hermes plugins enable tam
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).
Read-only Home Assistant Recorder statistics tools (ha_list_statistics and ha_get_statistics).
Good to know before installing
Each call opens an authenticated WebSocket connection to the configured Home Assistant instance using the active profile HASS_TOKEN; returned statistic metadata and values become agent tool results and may reach the configured model provider. No telemetry, shell commands, background processes, credential storage or direct database access.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs HASS_TOKEN), then asks whether to turn it on.
hermes plugins install homeassistant-statistics
Said no? Turn it on later:
hermes plugins enable homeassistant-statistics
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.
Wicked Memory
Community
Persistent, wallet-scoped long-term memory for Hermes: remember, semantic recall, versioned update, history and approved hard delete, backed by the hosted Wicked Memory service, plus skills for using it and for…
Persistent, wallet-scoped long-term memory for Hermes: remember, semantic recall, versioned update, history and approved hard delete, backed by the hosted Wicked Memory service, plus skills for using it and for connecting the Wicked MCP server. Works with no setup (a wallet is generated on first use; search uses the service's shared free key).
Good to know before installing
Sends the memory text and search queries the agent chooses to memory.wickedapi.com (or your configured base_url), each request signed by the agent's wallet, plus one GET to /v1/status on first use to read the published community key; stores a generated private key unencrypted in the plugin data dir unless you supply WICKED_MEMORY_PRIVATE_KEY; no shell commands, no background processes, no telemetry; every wicked_memory_forget asks for human approval. The bundled wicked-suite-mcp skill walks you through adding the author's hosted Wicked MCP server (https://mcp.wickedapi.com/mcp, 75 tools, some x402-priced); that server is a separate manual step and is not covered by this pin.
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 wicked-memory
Said no? Turn it on later:
hermes plugins enable wicked-memory
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.
Jev Effort Router
Community
Per-turn model AND reasoning-effort routing, decided by TypeSafe Jev, which rewrites the outgoing Ollama:Cloud provider request itself via the llm_request middleware.
Per-turn model AND reasoning-effort routing, decided by TypeSafe Jev, which rewrites the outgoing Ollama:Cloud provider request itself via the llm_request middleware. Every other catalog router picks a model and stops, and the two entries that touch reasoning effort move it by hand; this one decides both per turn. Ollama:Cloud only — no other provider is routed, and every failure path leaves the request byte-identical to a plugin-disabled run.
Good to know before installing
Sends the current user message and up to 4 previous turns to OpenRouter's Decisions API (typesafe/jev, billed to your OpenRouter key) on every routed turn.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs OPENROUTER_API_KEY), then asks whether to turn it on.
hermes plugins install jev-effort-router
Said no? Turn it on later:
hermes plugins enable jev-effort-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.
Gbrain Plugin
Community
Community (non-official) plugin wiring GBrain (garrytan/gbrain, MIT) into Hermes as a local memory layer over MCP: /gbrain status command, desktop starter, and per-profile Postgres setup/update/maintenance scripts.
Community (non-official) plugin wiring GBrain (garrytan/gbrain, MIT) into Hermes as a local memory layer over MCP: /gbrain status command, desktop starter, and per-profile Postgres setup/update/maintenance scripts. Not affiliated with upstream.
Good to know before installing
The plugin itself only adds a /gbrain status command and a Desktop pane; GBrain is installed by the user via scripts/setup.sh, which installs bun (curl|bash), an unpinned gbrain from GitHub HEAD, and provisions PostgreSQL with sudo.
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 gbrain-plugin
Said no? Turn it on later:
hermes plugins enable gbrain-plugin
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).
Native Kiro model provider over HTTPS with AWS Builder ID / IAM Identity Center device login.
Good to know before installing
Dynamically registers an AWS OIDC public client named `hermes-kiro` during login and stores OAuth grants in Hermes' profile-scoped auth.json credential pool.
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 kiro-provider
Said no? Turn it on later:
hermes plugins enable kiro-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).
Local Markdown memory provider with multilingual lexical recall and profile-local durable notes. Create-only writes are limited to primary agent contexts. Uses published birkin-mnemosyne 0.7.2 with compatible updates below 1.0; no API key, network service or telemetry. Session handoff capture is opt-in. Native Hermes memory files remain separate.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install birkin-mnemosyne
Said no? Turn it on later:
hermes plugins enable birkin-mnemosyne
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.
Liquid Inference Provider
Community
Liquid Inference, an auction exchange for LLM inference, as a Hermes model provider (provider id `liquid`): the exchange sends each request to the eligible offer with the lowest estimated charge, and each request…
Liquid Inference, an auction exchange for LLM inference, as a Hermes model provider (provider id `liquid`): the exchange sends each request to the eligible offer with the lowest estimated charge, and each request carries a cap on its charge (1 USD by default; set `model.default_headers.x-liquid-cap-usd` to change it). Submitted by Architect, the operator of Liquid Inference.
Good to know before installing
Registers one model provider at import and nothing else (no tools, hooks, commands or threads). Chat requests (full prompts and tool results), auxiliary tasks (model `liquid.auto`) and the model list go through Hermes's own client to https://router.inference.ai.exchange/v1 (or LIQUID_BASE_URL) with LIQUID_API_KEY. The exchange forwards each request to whichever third-party provider wins its auction. Each request is billed up to its `x-liquid-cap-usd` cap (1 USD by default, set with `model.default_headers.x-liquid-cap-usd`) and carries `X-Title: Hermes Agent`. A top-level `reasoning_effort` is sent only when you select a level.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs LIQUID_API_KEY), then asks whether to turn it on.
hermes plugins install liquid-inference-provider
Said no? Turn it on later:
hermes plugins enable liquid-inference-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).
Local-only web dashboard for browsing and visualising Mnemosyne memories, triples, stats, and consolidation history.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install mnemosyne-dashboard
Said no? Turn it on later:
hermes plugins enable mnemosyne-dashboard
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).
Direct Mistral Vibe subscription access — browser PKCE login, dedicated credential pool, account-visible catalog discovery, relay-verified reasoning_effort for GLM models.
Good to know before installing
Unofficial, not affiliated with Mistral. "hermes auth add mistral-vibe" runs a browser PKCE sign-in against Mistral's Vibe console endpoints (console.mistral.ai/api/vibe/*) and stores the returned API key in the Hermes credential pool (auth.json, slice mistral-vibe), or uses MISTRAL_VIBE_API_KEY. Prompts and model listing go only to api.mistral.ai/v1. Vibe subscription coverage of API use is not guaranteed and may bill as pay-as-you-go. Logout clears the local pool but does not revoke the key remotely.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs MISTRAL_VIBE_API_KEY), then asks whether to turn it on.
hermes plugins install mistral-vibe
Said no? Turn it on later:
hermes plugins enable mistral-vibe
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.
Cognition
Community
Cognition session-end memory — facts regex-extracted from your messages at session end, stored in a local SQLite queue and JSON log under one repo label, with fetch-first merge, per-entry provenance, and budgeted…
Cognition session-end memory — facts regex-extracted from your messages at session end, stored in a local SQLite queue and JSON log under one repo label, with fetch-first merge, per-entry provenance, and budgeted prefetch (tools: cognition_search, cognition_status, read-only cognition_dream).
Good to know before installing
Saves verbatim excerpts (up to 400 chars) of your own messages that match preference/decision phrases in plain local files under HERMES_HOME/cognition/ (SQLite queue, JSON commit log) and re-injects them into later prompts sent to your model provider; the author name is read from ~/.gitconfig; the plugin makes 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 cognition
Said no? Turn it on later:
hermes plugins enable cognition
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).
Per-call delegation across your own subscriptions. The model sends each subagent to a named route with delegate_to(route, goal, context); each route pins a provider Hermes already knows (Claude, Codex or Antigravity subscription plugins, ACP provider plugins) and a model. delegate_task, by contrast, uses the one target in config.yaml. Subagents launch through ctx.subagent_lifecycle. A child counts as out of quota only on an unambiguous provider error or a measured window at 100 %, and the route never switches on its own: a policy decides whether the parent asks you, picks another route, or waits.
Good to know before installing
A pre_tool_call hook blocks delegate_task spawns while routes are configured (list/steer/stop pass); an api_request_error hook records quota errors in memory. Quota is read with Hermes' fetch_account_usage (Anthropic and OpenAI Codex) on /ohx quota and after a provider error. No other network egress, no files written.
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 orquehelx
Said no? Turn it on later:
hermes plugins enable orquehelx
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.
Dexio
Community
Dexio shared-wiki memory. Before each turn, the pages of your Dexio wiki that match the user's message; tools to search, read and write the pages your other agents and team also use.
Dexio shared-wiki memory. Before each turn, the pages of your Dexio wiki that match the user's message; tools to search, read and write the pages your other agents and team also use. Nothing is captured automatically: no transcripts or turn logs. Standard library only; no background threads or local services.
Good to know before installing
With DEXIO_API_KEY set, the first 300 characters of each user message go to the Dexio server (default app.dexio.wiki, or DEXIO_URL) as a search query, tool arguments and the agent's profile name go there on tool calls, and the model is prompted to write, overwrite and edit pages in a wiki shared with the user's team and other agents, without a confirmation step.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs DEXIO_API_KEY), then asks whether to turn it on.
hermes plugins install dexio
Said no? Turn it on later:
hermes plugins enable dexio
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.
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).
Shared fleet memory for Hermes agents: every connected agent learns from all other agents connected to the memory, wherever they run. Sessions across machines and harnesses are distilled into one common brain overnight — what one learns, the whole fleet recalls. Pushes a compact per-turn recall index (entries lazy-load via hicortex_get), injects fresh lessons plus a per-agent standing context block at session start — lesson blocks are delimited and carry an explicit reference-data framing line and provenance header — and exposes the full 9-tool memory surface (search, get, recent, ingest, lessons, index, graph, update, delete) through the shared server. The same server also serves Claude Code, OpenClaw, Pi and opencode agents, so mixed-harness fleets share one brain. Stdlib-only, no pip dependencies. Requires a running Hicortex server (npx @gamaze/hicortex init on any machine); data flow: each user message is sent to your configured Hicortex server for recall (default http://localhost:8787); session distillation runs on the server.
Good to know before installing
Sends every user message (and profile name) to your configured Hicortex server each turn for recall, default http://localhost:8787, plain http with a bearer token is accepted for remote servers with a one-time log warning; the server's standing Identity text and lessons are injected into the system prompt; the model can permanently update or delete shared fleet memories via hicortex_update / hicortex_delete without confirmation.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs HICORTEX_URL, HICORTEX_AUTH_TOKEN), then asks whether to turn it on.
hermes plugins install hicortex
Said no? Turn it on later:
hermes plugins enable hicortex
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.
Brethof Brain
Community
brethof-brain long-term memory provider — the memory's briefing in the system prompt at session start, ambient recall on every turn, every turn archived.
brethof-brain long-term memory provider — the memory's briefing in the system prompt at session start, ambient recall on every turn, every turn archived; one memory shared with the user's other agents (Claude Code, Codex, OpenCode and more). Sends each turn to the user's own brethof-brain memory (on their machine at 127.0.0.1:8610, or hosted at memory.brethof.cloud). Needs a brethof-brain account.
Good to know before installing
Sends every user prompt and each turn's user and assistant text, with your API key, to the brethof-brain server you configure (default a local box at 127.0.0.1:8610; hosted at memory.brethof.cloud), and puts the server's returned briefing and recall text into the system prompt and each turn; reads BRETHOF_BRAIN_* from $HERMES_HOME/.env and ~/.brethof-brain/config.json.
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 brethof-brain
Said no? Turn it on later:
hermes plugins enable brethof-brain
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).
Cashew — persistent thought-graph memory with local embeddings, organic decay, and autonomous think cycles.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install cashew
Said no? Turn it on later:
hermes plugins enable cashew
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.
Provenance Gate
Community
Flags memory and skill_manage writes that state a user decision ("the user decided ...", "用户决定 ...") without the user's own words: each such sentence needs a quote that appears verbatim in text the user typed in this…
Flags memory and skill_manage writes that state a user decision ("the user decided ...", "用户决定 ...") without the user's own words: each such sentence needs a quote that appears verbatim in text the user typed in this session, shares key words with the decision and does not drop a negation. A patch is checked by the text it produces. Observe mode (the default) records flagged writes and `hermes provenance-gate report` lists them; block mode refuses them and tells the model how to fix the write. Measured on an independent blind set of 133 lines: precision 1.000, recall 0.694.
Good to know before installing
Two hooks (pre_llm_call, pre_tool_call); keeps a local copy of the text the user types, with its sender_id and session link, and an evidence log of checked claims under plugin-data/provenance-gate (30-day default retention, `hermes provenance-gate purge`); reads MEMORY.md, USER.md and skill files to reproduce what a patch produces; no network, no credentials, never asks for approval.
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 provenance-gate
Said no? Turn it on later:
hermes plugins enable provenance-gate
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).
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install lancedb
Said no? Turn it on later:
hermes plugins enable lancedb
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).
Local-first persistent memory: store durable facts once and recall them in any session. Portable Agent Plugins v1 package (mcp.json + skills/): the @mem-os/sdk MCP server (pinned 1.6.26) over npx stdio, plus the mem-os-memory skill covering when to store and when to recall. All data stays in a local SQLite database under the user home directory; no cloud, no telemetry, no API keys. Server cwd is ${PLUGIN_DATA} so nothing is written into the install tree. Needs Node.js and npm on PATH.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install mem-os
Said no? Turn it on later:
hermes plugins enable mem-os
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).
MindGraph — semantic graph memory with hybrid retrieval, goal/decision tracking, and cross-document synthesis.
How to install
Install it. Hermes asks for any API keys it needs (this one needs name), then asks whether to turn it on.
hermes plugins install mindgraph
Said no? Turn it on later:
hermes plugins enable mindgraph
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.
Lumberroom
Community
lumberroom memory provider. One durable store shared with every agent you use, recalled on every turn and written through the engine's own memory_write.
lumberroom memory provider. One durable store shared with every agent you use, recalled on every turn and written through the engine's own memory_write. Self-hosted open-source engine or lumberroom.cloud; OAuth or a static token. Maintained by the lumberroom team.
Good to know before installing
When active, every non-trivial user message (first 1,000 characters) and the absolute git-root path of the working directory are sent on each turn to the configured lumberroom engine, which defaults to https://mcp.lumberroom.cloud (operated by Cybersapien Technologies, India) unless base_url names a self-hosted engine; the model is instructed to store decisions, preferences and facts there through memory_write, the engine's live tool descriptions and server instructions are injected into the system prompt each session, and setup switches off Hermes' built-in MEMORY.md/USER.md 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 lumberroom
Said no? Turn it on later:
hermes plugins enable lumberroom
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).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Mnemostack
Community
Persistent agent memory over a mnemostack service or a local Qdrant — hybrid recall (vector + lexical + graph), verbatim capture with self-echo suppression, and soft retraction.
Persistent agent memory over a mnemostack service or a local Qdrant — hybrid recall (vector + lexical + graph), verbatim capture with self-echo suppression, and soft retraction. Multi-tenant when pointed at a shared authenticated service; the tenant is resolved server-side from the service key.
Good to know before installing
The pinned directory is a discovery shim; the provider code installs from PyPI at the version pinned in plugin.yaml pip_dependencies (hermes-mnemostack==1.0.3) into the Hermes venv. Configured via MNEMOSTACK_* env vars; no key is required for a purely local Qdrant setup.
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 mnemostack
Said no? Turn it on later:
hermes plugins enable mnemostack
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).
Full setup steps, settings and screenshots are on the plugin's official catalog page from Nous Research.
Hermes Pubky
Community
Setup helper for managed Pubky agents. The launcher syncs agent state, including conversation database snapshots and portable configuration, to your remote Pubky homeserver.
Setup helper for managed Pubky agents. The launcher syncs agent state, including conversation database snapshots and portable configuration, to your remote Pubky homeserver.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install hermes-pubky
Said no? Turn it on later:
hermes plugins enable hermes-pubky
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.
Lancedb Suite
Community
Local-first LanceDB vector memory with a strict write contract, calibrated abstention, typed relations, conflict tracking and a retrieval-quality gate.
Local-first LanceDB vector memory with a strict write contract, calibrated abstention, typed relations, conflict tracking and a retrieval-quality gate. Requires local Ollama + nomic-embed-text.
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install lancedb-suite
Said no? Turn it on later:
hermes plugins enable lancedb-suite
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).
Use the signed-in Aside browser as Hermes's browser when the Aside CLI is installed.
Good to know before installing
Runs the local aside CLI to drive your signed-in Aside browser (page text, screenshots, Aside memory, model-written JavaScript via aside_repl) without a Hermes approval prompt; Aside's permission level is a user-only setting (default ask) that covers aside_exec only. Optional pre_tool_call hook blocks Hermes' built-in browser tools while Aside is ready when browser_policy is always. Reads Aside's settings.json for the model list; 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 aside-browser
Said no? Turn it on later:
hermes plugins enable aside-browser
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).
Read-only memory.provider for GBrain (garrytan/gbrain, MIT; not affiliated). After each non-trivial turn it searches a GBrain MCP server (`gbrain serve --http`) in the background and injects up to the configured limit (3 by default, capped at 10) of `[source:slug] title` pointers into the next turn as fallible background context. It never writes to GBrain and adds no tools or hooks.
Good to know before installing
After each non-trivial turn, the first 500 characters of your message are sent to GBRAIN_MCP_URL (default http://127.0.0.1:3131/mcp; plain http to a non-loopback host is refused unless GBRAIN_POINTER_ALLOW_HTTP=1), and the profile's GBrain OAuth client id and secret go to that server's /token endpoint. Redirects and proxy settings are ignored. Only the slug, title and source id of up to 10 results are kept and injected into the next turn as background context; rows GBrain flags as suspected injection are skipped. Tokens and pointers stay in memory only. It never writes to GBrain; no other network calls, no telemetry.
From the plugin's catalog listing.
How to install
Install it. Hermes asks for any API keys it needs (this one needs GBRAIN_MCP_CLIENT_ID, GBRAIN_MCP_CLIENT_SECRET), then asks whether to turn it on.
hermes plugins install gbrain-pointer
Said no? Turn it on later:
hermes plugins enable gbrain-pointer
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).
GitHub and GitHub Enterprise tools with bot-first attribution and approval-gated issue/PR writes.
Good to know before installing
Authenticates as a GitHub App from GITHUB_APP_ID, GITHUB_APP_INSTALLATION_ID and a private key in GITHUB_APP_PRIVATE_KEY or GITHUB_APP_PRIVATE_KEY_PATH/_FILE (read from the profile env or HERMES_HOME/.env, held in memory only, never written or logged), falling back to GITHUB_TOKEN/GH_TOKEN or `gh auth token` when no App variables are set, and reports which identity acted in every result. Talks only to https://api.github.com or the operator-configured GITHUB_API_URL / settings.api_url (HTTPS, no redirects; no tool argument can change the host). Issue/comment/review/merge writes stay disabled until settings.allow_write_actions is true and each one additionally goes through Hermes's human-approval prompt via its pre_tool_call hook (an 'always' answer does not persist).
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 github_app
Said no? Turn it on later:
hermes plugins enable github_app
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).
Community Zvec memory backend for Hermes Agent - in-process HNSW + RocksDB FTS store with native hybrid retrieval and session-safe lock governance; embeddings via any Ollama-compatible endpoint (local Ollama bge-m3 by default).
How to install
Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install memory-zvec
Said no? Turn it on later:
hermes plugins enable memory-zvec
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).
Persistent memory for agents, shared across tools: save preferences, decisions and lessons and recall them later by natural-language search; rating a recalled memory as helpful or misleading re-ranks what comes back next; shared rooms (beta) let several people's agents work from one memory. Portable Agent Plugins v1 package (plugin.json + mcp.json + skills/) pointing at the hosted Mnemoverse MCP server (Streamable HTTP, OAuth 2.1 + DCR); the two bundled skills load under a namespaced name.
Good to know before installing
Hosted-only connector; Hermes runs no code from the package (scripts/ holds the repository's own CI checks). Every tool call goes to the vendor's remote MCP server at mcp.mnemoverse.com (authorization server auth.mnemoverse.com, browser sign-in on console.mnemoverse.com); memories the agent writes are stored in the signed-in user's Mnemoverse account, and recalled memories are pulled into the session context. OAuth tokens are held and refreshed by Hermes, never by the package. No telemetry, background process or self-update code.
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 mnemoverse
Said no? Turn it on later:
hermes plugins enable mnemoverse
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).
Durable memory and context compression for Hermes Agent with local SQLite or flat-file storage.
Good to know before installing
Replaces the memory provider (memory.provider: nachos) and, only when context.engine: nachos is set, the context engine; the provider injects a system-prompt block telling the agent to use the nachos_memory_* tools and keep built-in memory disabled; opt-in semantic ranking either runs a separately installed nachos-embeddings CLI or sends the turn query plus memory titles/summaries to api.openai.com with OPENAI_API_KEY; all storage is local under $HERMES_HOME/nachos/.
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 nachos
Said no? Turn it on later:
hermes plugins enable nachos
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).
Desktop-only, read-only monitor for pending memory and skill write approvals.
Good to know before installing
The pane's API reads pending/memory/*.json and pending/skills/*.json under the default Hermes root and every named profile directory beneath it (all profiles, not only the active one), and returns only counts, age buckets, oldest age, and per-item profile/subsystem/id/action/origin/created_at/age_seconds. It never returns or displays summaries, payloads, or record content; it exposes no approve, reject, or delete actions; it registers no tools, hooks, or middleware, performs no network I/O, and holds no credentials.
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 pending-queue-monitor
Said no? Turn it on later:
hermes plugins enable pending-queue-monitor
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).
Automatic recall sends the first 4,000 characters of each nontrivial local prompt to app.mypenny.ai as a search query, and the agent can save notes there through penny_remember without a Hermes approval prompt; works only in local CLI/TUI conversations (cron, subagents and gateways are refused); login is a manual command that registers its own OAuth client with clerk.mypenny.ai and briefly listens on 127.0.0.1 for the callback; tokens are kept in <HERMES_HOME>/penny/auth.json (owner-only) and are not removed on uninstall; no raw transcript upload, telemetry or other-client credential reuse.
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 penny
Said no? Turn it on later:
hermes plugins enable penny
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.
Cortexlayer
Community
CortexLayer memory provider — page-linked long-term memory with link-expansion retrieval, wired into Hermes' automatic per-turn recall (prefetch) and persistence (sync_turn), plus a pre-compress checkpoint so evidence…
CortexLayer memory provider — page-linked long-term memory with link-expansion retrieval, wired into Hermes' automatic per-turn recall (prefetch) and persistence (sync_turn), plus a pre-compress checkpoint so evidence Hermes' own context compaction would otherwise drop is saved first. Platform mode only: each turn's query and conversational content is sent to the hosted api.cortexlayer.net (HTTPS, API-key authenticated) for storage/retrieval — no local/offline mode. Requires a free CortexLayer account and API key.
How to install
Install it. Hermes asks for any API keys it needs (this one needs CORTEX_API_KEY), then asks whether to turn it on.
hermes plugins install cortexlayer
Said no? Turn it on later:
hermes plugins enable cortexlayer
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).
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.
