Long-term memory store for Hermes agents across sessions
Adds persistent memory to your Hermes agent so it can remember context, user preferences, and past interactions across sessions. Uses a local vector store by default.
Low blast radius on the evidence available, but it is still third-party code — a quick look at the SKILL.md costs nothing.
It queries a database or persistent store. Prefer a read-only credential unless it genuinely needs to write.
This skill's own description refers to "vector store"
These permissions are inferred from this listing — the credentials it declares, any maintainer warning, and the operations its own description mentions. ClawVault has not audited this skill's source code. Treat it as a starting point for your own review, not a substitute for one.
Hermes skills are on-demand knowledge documents stored in hermes/skills/, which is the single source of truth. Bundled skills are copied there on a fresh install, and hub-installed and agent-created skills land there too. Every installed skill automatically becomes a slash command, so a skill named plan is invoked with /plan.
hermes skills search memoryAdd --source to widen the search: official for curated skills, skills-sh for the public skills.sh directory, browse-sh for site-specific browser automation, or well-known to point Hermes at a site publishing its own skill index.
hermes skills inspect official/<category>/memoryinspect shows the skill's contents and metadata. Use the fully qualified identifier that search returned, which includes its source and category.
hermes skills install official/<category>/memoryIdentifiers are source-qualified, for example official/migration/openclaw-migration or skills-sh/anthropics/skills/pdf. You can also install straight from a URL that serves a SKILL.md. --force overrides non-dangerous policy blocks but will not override a dangerous scan verdict.
/memoryInstalled skills become slash commands in any chat session. Run hermes skills list to see everything available, or /skills from inside a session.
Commands follow the official Hermes Agent documentation. Placeholders such as <owner> are filled in by the search step, because registry references are publisher-scoped.
Hermes checks third-party and community skills against policy before installing, and --force will not override a verdict it considers dangerous. Because Hermes can also write its own skills at runtime, review what the Curator has kept periodically with hermes skills list.
Deploy OpenClaw, Hermes, or PicoClaw on Bluehost with the right template for the job.
Capability Evolver is the most downloaded skill on ClawHub with over 35,000 installs and it earns that position. It is a meta-skill that lets your OpenClaw agent analyse its own runtime history, identify failures or inefficiencies, and autonomously update its approach to improve performance over time. If a task fails three times in a row, Evolver detects the pattern and either creates a workaround or adjusts the agent's behaviour without you doing anything. Think of it as a personal trainer running silently in the background. Over weeks of use the improvement is measurable — faster task completion, fewer retries, more accurate outputs.
GOG is the go-to Google Workspace skill on ClawHub with over 14,000 downloads and the most complete implementation available. A single installation gives your OpenClaw agent full access to Gmail, Google Calendar, Google Drive, Google Docs, Google Sheets and Google Contacts through one consistent connection. Instead of installing and configuring five separate Google skills, GOG handles all of them through a unified OAuth flow. For anyone whose work life runs through Google Workspace, this skill transforms OpenClaw into a genuine productivity assistant.
Memory LanceDB is OpenClaw's vector-based long-term memory plugin and one of the most impactful skills you can add to any agent running 24/7 on a VPS. Unlike basic memory that stores conversation history as flat text, LanceDB uses vector embeddings to store and retrieve memories semantically — meaning your agent can recall relevant past context even when you phrase a question differently. Every task, preference, outcome and piece of information your agent encounters gets stored and becomes searchable. The longer the agent runs the more useful it becomes.