New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

mem9 Memory Plugin Setup

by mem9-ai in mem9-ai/mem9

Routes setup, troubleshooting and uninstall flows for mem9, a persistent cloud memory plugin for OpenClaw, and defines strict rules for config keys and API key handling.

Apache-2.0Auto-check passedAgent Workflows

Install mem9 Memory Plugin Setup

skills CLI
$ npx skills add mem9-ai/mem9 --skill mem9 -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mem9-ai/mem9 mem9 --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mem9-ai/mem9.git skills-src && mkdir -p .claude/skills && cp -r skills-src/site/public .claude/skills/mem9 && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
mem9
GitHub stars
1.2k
Token cost
~1.4k tokens
SKILL.md length
635 words
Files
20
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

Routes setup, troubleshooting and uninstall flows for mem9, a persistent cloud memory plugin for OpenClaw, and defines strict rules for config keys and API key handling.

  • Installing the mem9 memory plugin for OpenClaw for the first time
  • SKILL.md covers What This Skill Does, Source / Runtime Authority, Allowed Config Scope and Routing, plus 1 more section
  • Calls npm; reaches api.mem9.ai
  • Troubleshooting a broken or incomplete mem9 setup

What it does

This top-level document routes first-time install, reconnect, config review and mainland China or Alibaba Cloud npm handling to SETUP.md, setup failures and broken local state to TROUBLESHOOTING.md, and local removal to UNINSTALL.md. It is a routing and safety document, not the canonical reference for runtime request behavior.

Install rules are strict: mem9 is installed only through openclaw plugins install, never a global npm install, because OpenClaw does not discover global packages as plugins. Only plugins.entries.mem9.config.apiKey is a valid config key, never plugins.entries.mem9.apiKey, and OpenClaw 4.23 or later needs plugins.entries.mem9.hooks.allowConversationAccess set to true so mem9 can read conversation messages during agent_end.

Setup verification stays deterministic: if the first post-restart message produces no key, the one local OpenClaw agent trigger from SETUP.md runs in that same turn instead of asking for repeated test messages. A missing API key during create-new mode is not treated as failure until the generated key is verified. API keys are kept out of local memory and history notes during setup and shown only in the final onboarding handoff message, and history import from local session files stays manual.

When your agent uses it

  • Installing the mem9 memory plugin for OpenClaw for the first time
  • Troubleshooting a broken or incomplete mem9 setup
  • Uninstalling mem9 from a local machine
  • Checking which config keys are valid for the mem9 plugin

Example prompts

  • “Set up mem9 for OpenClaw and connect my API key.”
  • “My mem9 reconnect isn't working. Help me troubleshoot it.”
  • “Uninstall mem9 from this machine.”

Requirements

  • OpenClaw, version 4.23 or later for conversation-access hooks

What it can do on your machine

Read from SKILL.md and the folder at commit 071a4e8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.mem9.ai

    Also links to:

    • mem9.ai

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

mem9 Memory Plugin Setup loads about 1.4k tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 635 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mem9-ai/mem9 at commit 071a4e8, republished under its Apache-2.0 licence (© mem9-ai). 635 words, ~1,381 tokens.

Download SKILL.mdSave it as .claude/skills/mem9/SKILL.md (or your agent's skills folder). This skill also uses 19 other files; get the full folder from GitHub.
name
mem9
description
Persistent cloud memory plugin for OpenClaw. This document routes setup, troubleshooting, and uninstall flows and defines config boundaries.
version
1.0.49
homepage
https://mem9.ai/openclaw-memory
keywords
mem9, openclaw memory, persistent memory, cloud memory, memory plugin, setup mem9, install mem9, reconnect mem9, uninstall mem9
user-invocable
true

mem9

mem9 is the persistent cloud memory plugin for OpenClaw. It keeps durable memory across sessions and machines.

This top-level SKILL.md is a routing and safety document. It is the entry point for setup, troubleshooting, and uninstall flows. It is not the canonical reference for runtime request behavior.

What This Skill Does

  • Route first-time install, reconnect, config review, and mainland China / Alibaba Cloud npm install handling to SETUP.md.
  • Route setup failures, recovery work, and broken local state to TROUBLESHOOTING.md.
  • Route local mem9 removal on this machine to UNINSTALL.md.
  • Preserve filtered utm_* params from a remote SKILL.md URL through the create-new setup flow and first restart.
  • Install mem9 only through openclaw plugins install @mem9/mem9; never substitute npm install -g @mem9/mem9, because OpenClaw does not discover global npm packages as plugins.
  • Prevent invalid compatibility fallbacks: never write plugins.entries.mem9.apiKey; only plugins.entries.mem9.config.apiKey is valid.
  • Configure OpenClaw 4.23+ hook permission with plugins.entries.mem9.hooks.allowConversationAccess = true so mem9 can read conversation messages during agent_end.
  • Keep create-new verification deterministic: if the first post-restart return message does not produce a key, run the one local OpenClaw agent trigger from SETUP.md in that same resumed turn; never ask for repeated hi messages.
  • In create-new mode, do not treat missing plugins.entries.mem9.config.apiKey as failure. The generated key is verified from mem9 logs or local provision state until the user explicitly reconnects with it.
  • Enforce the setup success onboarding handoff: every successful create-new or reconnect setup must end with the template that starts ✅ Your mem9 API key is connected. followed by 🧭 WHAT YOU CAN DO NEXT; never replace it with a brief success summary.
  • Keep API keys out of local memory/history notes during setup. Do not write the full key or a key preview into MEMORY.md, memory/*.md, or equivalent local logs; show the key only in the final onboarding handoff.
  • Keep restart notices honest: only claim post-restart verification has resumed after that work has actually started.
  • Keep history import manual. Do not scan or upload local memory or session files from this skill.

Source / Runtime Authority

  • Official source: mem9-ai/mem9 and mem9.ai.
  • Default setup network target is https://api.mem9.ai unless the user explicitly chooses another apiUrl.
  • The installed mem9 plugin contains the actual OpenClaw integration, request logic, default base URL handling, and runtime behavior.
  • This SKILL.md is not the backend API contract and does not define day-to-day memory semantics.
  • For OpenClaw-specific runtime details, use the plugin README: openclaw-plugin/README.md.
Show full SKILL.md (243 more words)Show less

Allowed Config Scope

Only these openclaw.json paths may be changed during setup:

  • plugins.slots.memory
  • plugins.entries.mem9.enabled
  • plugins.entries.mem9.hooks.allowConversationAccess for OpenClaw 4.23+ / 2026.4.22+ only
  • plugins.entries.mem9.config.apiUrl
  • plugins.entries.mem9.config.apiKey
  • plugins.entries.mem9.config.provisionToken for create-new only; generate it once per create-new run before the first restart and keep it stable through the first successful post-restart provision on this machine
  • plugins.entries.mem9.config.provisionQueryParams for create-new only, and only when the remote SKILL.md URL contains filtered utm_* parameters; when present, it must be written before the first restart
  • plugins.allow

Do not change any other config keys unless the user explicitly asks.

The scope above is exhaustive. In particular, do not write plugins.entries.mem9.apiKey at the entry top level. OpenClaw rejects that key as invalid config before the mem9 plugin can load.

Routing

  • Install, enable, reconnect, or review mem9 config changes: read SETUP.md.
  • Setup failures, broken reconnects, local cleanup issues, or recovery guidance: read TROUBLESHOOTING.md.
  • Uninstall, remove, disable, or roll back mem9 on this machine: read UNINSTALL.md.
  • If an uninstall request also mentions reset session, restart gateway, 重启网关, clearing local mem9 history, or equivalent, still route to UNINSTALL.md first and keep those actions as post-verification follow-up only.
  • If this skill is loaded remotely, resolve SETUP.md, TROUBLESHOOTING.md, and UNINSTALL.md relative to the directory containing the current SKILL.md.

Definition of Done

  • The correct supporting document was used for the user's intent: SETUP.md, TROUBLESHOOTING.md, or UNINSTALL.md.
  • No openclaw.json paths outside the allowed scope were changed.
  • Runtime behavior claims defer to the installed plugin and its README, not to this top-level routing document.

© mem9-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 19 other files in site/public of mem9-ai/mem9.

  • SKILL.md
  • SETUP.md
  • TROUBLESHOOTING.md
  • UNINSTALL.md
  • _meta.json
  • favicon.svg
  • logo.png
  • mem9-github-square.png
  • mem9-github-square.svg
  • mem9-mark.svg
  • mem9-wordmark-dark-square.png
  • mem9-wordmark-dark-square.svg
  • mem9-wordmark-square.png
  • mem9-wordmark-square.svg
  • mem9-wordmark.png
  • mem9-wordmark.svg
  • qr-code-install-mem9.png
  • release-notes-hero.jpg
  • tidb-logo.png
  • tidb-logo.svg

Open the folder on GitHubat commit 071a4e8

Compare with similar skills

mem9 Memory Plugin Setup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

mem9 Memory Plugin Setup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
mem9 Memory Plugin Setup this skillmem9-ai/mem91.2k—~1.4kAutomated safety check: PassApache-2.0
Custom Mode Creator for claude-memthedotmack/claude-mem99k—~2.4kAutomated safety check: PassApache-2.0
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Beads Task Memorygastownhall/beads28k—~1.2kAutomated safety check: PassMIT
Reflect on Session Learningscursor/plugins10k5 repos~1.2kAutomated safety check: PassNone
MemPalace Memory SearchMemPalace/mempalace59k—~1.4kAutomated safety check: PassMIT

Similar skills

  • Custom Mode Creator for claude-mem

    thedotmack/claude-mem

    Walks you through creating, installing and verifying a custom claude-mem mode, including note types, tags and optional Telegram alerts for chosen memories.

    99k GitHub stars~2.4k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed

  • Beads Task Memory

    gastownhall/beads

    Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.

    28k GitHub stars~1.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Reflect on Session Learnings

    cursor/plugins

    Official

    Starts three parallel reviewer subagents over the current conversation transcript, then turns their findings into concrete edits to existing skills.

    10k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MemPalace Memory Search

    MemPalace/mempalace

    Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.

    59k GitHub stars~1.4k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Compound Learning Writer

    EveryInc/compound-engineering-plugin

    Records one solved and verified problem as a durable learning in the repository, but only when the reasoning is not already clear from the final code, tests or docs.

    25k GitHub stars~2k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from mem9-ai/mem9

  • Mnemos Memory Setup

    mem9-ai/mem9

    Deploys a mnemo-server instance, provisions a tenant, and wires persistent memory into OpenClaw, OpenCode or Claude Code.

    1.2k GitHub stars~895 tokensUpdated 10 days ago
    Auto-check: notes

Categories

Questions about mem9 Memory Plugin Setup

What does mem9 Memory Plugin Setup do?

Routes setup, troubleshooting and uninstall flows for mem9, a persistent cloud memory plugin for OpenClaw, and defines strict rules for config keys and API key handling. md. It is a routing and safety document, not the canonical reference for runtime request behavior.

When should I use mem9 Memory Plugin Setup?

mem9 Memory Plugin Setup fits situations like: installing the mem9 memory plugin for OpenClaw for the first time; troubleshooting a broken or incomplete mem9 setup; uninstalling mem9 from a local machine; checking which config keys are valid for the mem9 plugin.

How do I install mem9 Memory Plugin Setup in Claude Code?

Run `npx skills add mem9-ai/mem9 --skill mem9 -a claude-code`. Or copy the skill folder (site/public in mem9-ai/mem9) into .claude/skills/mem9 in your project. Claude Code loads it when a task matches its description.

How do I install mem9 Memory Plugin Setup in Codex?

Run `npx skills add mem9-ai/mem9 --skill mem9 -a codex`. Or copy the skill folder (site/public in mem9-ai/mem9) into .agents/skills/mem9 in your project. Codex loads it when a task matches its description.

Can I use mem9 Memory Plugin Setup in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mem9-ai/mem9 --skill mem9 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mem9, .gemini/skills/mem9, .github/skills/mem9 and .opencode/skills/mem9 in your project.

What does mem9 Memory Plugin Setup need to run?

Going by SKILL.md and its folder, mem9 Memory Plugin Setup needs the command-line tools its instructions call (npm). Our summary lists: OpenClaw, version 4.23 or later for conversation-access hooks.

Does mem9 Memory Plugin Setup access the network?

SKILL.md names 2 domains. In commands or code: api.mem9.ai; the agent is likely to contact it when it follows the instructions. As links in the text: mem9.ai. This is read from the text; nothing was executed.

Is mem9 Memory Plugin Setup safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does mem9 Memory Plugin Setup use?

mem9 Memory Plugin Setup is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does mem9 Memory Plugin Setup use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to mem9 Memory Plugin Setup?

Skills that share tags, products or a category with mem9 Memory Plugin Setup: Custom Mode Creator for claude-mem (thedotmack/claude-mem, 99k stars), Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars), Beads Task Memory (gastownhall/beads, 28k stars) and Reflect on Session Learnings (cursor/plugins, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains mem9 Memory Plugin Setup?

mem9-ai (a GitHub organization) maintains it in mem9-ai/mem9, which has 1,223 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 29, 2026.

Source: mem9-ai/mem9 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.