MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Persistent cloud memory for OpenClaw agents. An agent skill from LeoYeAI/openclaw-master-skills.
$ npx skills add LeoYeAI/openclaw-master-skills --skill mem9 -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills mem9 --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mem9-ai .claude/skills/mem9 && rm -rf skills-srcUse ~/.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/
Install the "mem9" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/mem9-ai into .claude/skills/mem9/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mem9", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/mem9-aiType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill mem9 -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills mem9 --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/mem9-ai .agents/skills/mem9 && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mem9" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/mem9-ai into .agents/skills/mem9/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mem9", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill mem9 -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills mem9 --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/mem9-ai .cursor/skills/mem9 && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mem9" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/mem9-ai into .cursor/skills/mem9/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mem9", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/mem9-ai--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill mem9 -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills mem9 --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/mem9-ai .gemini/skills/mem9 && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mem9" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/mem9-ai into .gemini/skills/mem9/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mem9", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills mem9Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill mem9 -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/mem9-ai .github/skills/mem9 && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mem9" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/mem9-ai into .github/skills/mem9/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mem9", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill mem9 -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills mem9 --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/mem9-ai .opencode/skills/mem9 && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mem9" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/mem9-ai into .opencode/skills/mem9/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mem9", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
mem9Persistent cloud memory for OpenClaw agents. An agent skill from LeoYeAI/openclaw-master-skills.
Mem9 is an agent skill from LeoYeAI/openclaw-master-skills. Persistent cloud memory for OpenClaw agents. Use when users say: - "install mem9" - "setup memory" - "add memory plugin" - "openclaw memory" - "mem9 onboarding" - "memory not working" - "import memories" - "upload sessions"
Its SKILL.md is about 5.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `_meta.json`).
It sits in Agent Workflows. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
curljqnpmFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
api.mem9.airegistry.npmmirror.comregistry.npmjs.orgFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Mem9 loads about 5.9k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 2,040 words of instructions outside code blocks.
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.
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.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 2,040 words, ~5,887 tokens.
.claude/skills/mem9/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.┌──────────────────────────────────────────────────────────────┐
│ │
│ ███╗ ███╗███████╗███╗ ███╗ █████╗ │
│ ████╗ ████║██╔════╝████╗ ████║██╔══██╗ │
│ ██╔████╔██║█████╗ ██╔████╔██║╚██████║ │
│ ██║╚██╔╝██║██╔══╝ ██║╚██╔╝██║ ╚═══██║ │
│ ██║ ╚═╝ ██║███████╗██║ ╚═╝ ██║ █████╔╝ │
│ ╚═╝ ╚═╝╚══════╝╚═╝ ╚═╝ ╚════╝ │
│ │
│ persistent memory for ai agents │
│ │
└──────────────────────────────────────────────────────────────┘mem9 gives OpenClaw persistent memory across resets, restarts, and new machines.
The plugin connects to one cloud memory space, identified by an API key.
When talking to end users:
apiKey when you are editing current OpenClaw plugin configtenantID only when explaining legacy compatibility or editing old raw configUse this skill when the user expresses intent to store, recall, or manage long-term memory.
Common triggers include:
Use this skill when the user wants OpenClaw to persist or manage long-term memory across sessions, devices, or restarts.
Typical situations include:
Do not use this skill for:
Good candidates:
Avoid storing:
If the user explicitly asks to remember something (for example: "remember this", "save this", "don't forget"), the agent should store the information using mem9 if mem9 is installed.
If mem9 is not installed yet, suggest installing mem9 to enable persistent memory.
This task is NOT complete until all of the following are true:
| Tool | When |
|---|---|
memory_store | Persist facts, decisions, context |
memory_search | Find the right memories by keywords and meaning |
memory_get | Retrieve by ID |
memory_update | Modify existing memory |
memory_delete | Remove |
Lifecycle hooks (automatic — no agent action needed):
| Hook | Trigger | What happens |
|---|---|---|
before_prompt_build | Every LLM call | Relevant memories injected as context |
before_reset | Before /reset | Session summary saved |
agent_end | Agent finishes | Last response captured |
Agents often finish the technical setup and forget to send the required final handoff. Prevent this by treating the handoff as part of the setup itself, not as optional follow-up.
Use this distinction consistently:
| Internal term | User-facing explanation |
|---|---|
apiKey | Preferred OpenClaw config field; sends the same mem9 API key in X-API-Key for v1alpha2 |
tenantID | Legacy OpenClaw config field; only mention for compatibility or old raw configs |
API_KEY env var | A local variable holding the user's mem9 API key |
secret | Treat as the same value as the mem9 API key unless the user clearly means something else |
| "recovery key" | Avoid this term; say "API key" instead |
Short rule: API key, apiKey, and secret may refer to the same mem9 identifier. Prefer saying API key to users, use apiKey in new config examples, and mention tenantID only as the legacy fallback alias.
Security note:
Treat the API key like a secret. Anyone who has it can access that mem9 space.
If the user asks "What is this for?" answer plainly:
This is the API key that reconnects you to your mem9 space. OpenClaw uses it to save and recall your memory in the right place.
If the user asks "What is the relationship between tenantID and key?" answer plainly:
You only need the API key. In current OpenClaw config, the preferred field is
apiKey.tenantIDis the legacy config field for the same value. Important: this API key is effectively your secret, so save it somewhere safe and never share it with anyone.
[AGENT] Ask the user before doing anything else:
Which setup do you want?
- Create a new mem9 API key
- Reconnect an existing mem9 API key
If you choose reconnect, paste your existing API key.
Heads-up: OpenClaw will restart later in this setup. When that happens, please wait a few minutes, then send "Hi" here to reconnect and continue.
Branching:
API_KEY="<paste-from-user>"When the user provides an existing API key, verify it is reachable before continuing:
curl -sf \
-H "X-API-Key: $API_KEY" \
"https://api.mem9.ai/v1alpha2/mem9s/memories?limit=1" \
&& echo "OK" || echo "UNREACHABLE"If the check returns OK, say:
Great, your existing mem9 API key is reachable. I will keep going and connect this setup to that same memory.
If the check fails, say:
I could not reach that API key. Please double-check it, or create a new mem9 API key instead.
If no — proceed to Step 1 to provision a new API key.
Skip this step if the user provided an existing API key in Step 0.
[AGENT]
curl -sX POST https://api.mem9.ai/v1alpha1/mem9s | jq .Response:
{
"id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}Save id as API_KEY.
When explaining it to the user, say:
Your new mem9 API key is ready. This API key is how this machine, and any future machine you trust, reconnects to the same memory.
Important: this API key is also your secret. Never share it with anyone. If someone else gets it, they can access your memory.
[AGENT] Detect npm registry reachability first. On mainland China / Alibaba Cloud networks, the default npm registry is often slow or unstable. Prefer a one-shot registry override instead of changing the user's global npm config.
NPMJS_TIME="$(curl -o /dev/null -sS --connect-timeout 2 --max-time 6 -w '%{time_total}' https://registry.npmjs.org/@mem9%2fmem9 || echo timeout)"
MIRROR_TIME="$(curl -o /dev/null -sS --connect-timeout 2 --max-time 6 -w '%{time_total}' https://registry.npmmirror.com/@mem9%2fmem9 || echo timeout)"
if [ "$MIRROR_TIME" != "timeout" ] && { [ "$NPMJS_TIME" = "timeout" ] || awk "BEGIN { exit !($NPMJS_TIME > 2 && $MIRROR_TIME < $NPMJS_TIME) }"; }; then
echo "Using China npm mirror: https://registry.npmmirror.com"
NPM_CONFIG_REGISTRY=https://registry.npmmirror.com openclaw plugins install @mem9/mem9
else
openclaw plugins install @mem9/mem9
fiDecision rule:
npmmirror is reachable, treat this as a China-optimized network path and use https://registry.npmmirror.com.npmmirror.npm config set registry ... globally unless the user explicitly asks for a permanent npm mirror change.Immediately after install completes, tell the user (before restarting anything):
✅ mem9 plugin installed. Next I need to restart the OpenClaw gateway so the plugin can load and the hooks/tools become active.
The restart will take about 1 minute. After that, send me a message to confirm mem9 is functional.
⚠️ Important (tool ordering): If you (the agent) are going to restart the gateway automatically via tools/exec, you must send the notice above as an outbound message first (e.g. via the message tool). Do not rely on the final assistant reply text, because tool calls happen before the final reply is delivered and a gateway restart can prevent that reply from being sent.
Then proceed to the gateway restart step for the user’s environment/profile.
After the restart completes, ask the user to wait ~1 minute and then send a quick message so you can confirm mem9 is working (for example: "Hello mem9").
[AGENT] Check the installed OpenClaw version before editing config:
openclaw --versionRouting rule:
>= 2.2.0, use the config path in Step 4A.< 2.2.0, use the config path in Step 4B.openclaw.json.[AGENT] Patch existing config (merge-safe, preserves other keys):
jq --arg api_key "$API_KEY" '
.plugins.slots.memory = "mem9" |
if (.plugins.entries.mem9.config // {}) == {}
then
.plugins.entries.mem9 = {
enabled: true,
config: { apiUrl: "https://api.mem9.ai", apiKey: $api_key }
}
else
.plugins.entries.mem9.config.apiKey = $api_key |
.plugins.entries.mem9.enabled = true
end |
.plugins.allow = ((.plugins.allow // []) + ["mem9"] | unique)
' openclaw.json > tmp.json && mv tmp.json openclaw.jsonNote: The allow array is additive—existing entries are preserved, mem9 is appended (deduplicated).
If mem9 config already exists, only apiKey is written; all other existing fields (such as apiUrl, agentName) are preserved.
Or if no openclaw.json exists, create:
{
"plugins": {
"slots": { "memory": "mem9" },
"entries": {
"mem9": {
"enabled": true,
"config": {
"apiUrl": "https://api.mem9.ai",
"apiKey": "<your-api-key>"
}
}
},
"allow": ["mem9"]
}
}[AGENT] No allow array needed:
jq --arg api_key "$API_KEY" '
.plugins.slots.memory = "mem9" |
if (.plugins.entries.mem9.config // {}) == {}
then
.plugins.entries.mem9 = {
enabled: true,
config: { apiUrl: "https://api.mem9.ai", apiKey: $api_key }
}
else
.plugins.entries.mem9.config.apiKey = $api_key |
.plugins.entries.mem9.enabled = true
end
' openclaw.json > tmp.json && mv tmp.json openclaw.jsonIf mem9 config already exists, only apiKey is written; all other existing fields are preserved.
Or if no openclaw.json exists, create:
{
"plugins": {
"slots": { "memory": "mem9" },
"entries": {
"mem9": {
"enabled": true,
"config": {
"apiUrl": "https://api.mem9.ai",
"apiKey": "<your-api-key>"
}
}
}
}
}Compatibility rule:
tenantID continue to work as a legacy alias for apiKeyapiToken or userTokenIf result returns stored memory → setup successful.
Restart OpenClaw so the new mem9 plugin config is loaded.
A setup is successful if all of the following are true:
[AGENT] After successful setup, the agent MUST send the following structured handoff before ending the task.
Do not summarize or remove any parts of it.
Translate the content into the user's language before sending, while keeping the same structure and all warnings.
✅ Your mem9 API key is ready.
🧭 WHAT YOU CAN DO NEXT
Import your existing local memory so mem9 starts with your real history.
Say: "import memories to mem9"
I can scan local memory notes and session files, then transform/import them into mem9.
Common local files include: memory/*.md, MEMORY.md, sessions/*.jsonl.
💾 YOUR MEM9 API KEY
API_KEY: <your-api-key>
This API key is your access key to mem9.
Keep it private and store it somewhere safe.
♻️ RECOVERY
Reinstall mem9 and use the same API_KEY in Step 4.
Your memory will reconnect instantly.
📦 BACKUP PLAN
Keep your original local memory/session files as backup.
Also store the API_KEY in a password manager or secure vault.Do not default to offering a synthetic write/read demo as the next step.
Preferred next-step order:
Base: https://api.mem9.ai
Preferred routes: /v1alpha2/mem9s/... with X-API-Key: <api-key>
Legacy routes: /v1alpha1/mem9s/{tenantID}/...
Header: X-Mnemo-Agent-Id: <name> (optional)
| Method | Path | Description |
|---|---|---|
| POST | /v1alpha1/mem9s | Provision tenant |
| GET | /healthz | Health check |
| POST | /v1alpha2/mem9s/memories | Create memory (X-API-Key) |
| GET | /v1alpha2/mem9s/memories | Search (?q=, ?tags=, ?source=, ?limit=) |
| GET | /v1alpha2/mem9s/memories/{id} | Get by ID |
| PUT | /v1alpha2/mem9s/memories/{id} | Update |
| DELETE | /v1alpha2/mem9s/memories/{id} | Delete |
| POST | /v1alpha2/mem9s/imports | Upload file (multipart) |
| GET | /v1alpha2/mem9s/imports | List import tasks |
| GET | /v1alpha2/mem9s/imports/{id} | Task status |
export API_KEY="your-api-key"
export API="https://api.mem9.ai/v1alpha2/mem9s"Store:
curl -sX POST "$API/memories" \
-H "Content-Type: application/json" \
-H "X-API-Key: $API_KEY" \
-d '{"content":"Project uses PostgreSQL 15","tags":["tech"],"source":"agent-1"}'Search:
curl -s -H "X-API-Key: $API_KEY" "$API/memories?q=postgres&limit=5"
curl -s -H "X-API-Key: $API_KEY" "$API/memories?tags=tech&source=agent-1"Get/Update/Delete:
curl -s -H "X-API-Key: $API_KEY" "$API/memories/{id}"
curl -sX PUT "$API/memories/{id}" -H "Content-Type: application/json" -H "X-API-Key: $API_KEY" -d '{"content":"updated"}'
curl -sX DELETE "$API/memories/{id}" -H "X-API-Key: $API_KEY"Import files:
# Read agent id from openclaw.json — same field the plugin uses at runtime (agents.list[].id).
# Falls back to plugins.entries.mem9.config.agentName if agents.list is absent.
AGENT_ID="$(jq -r '(.agents.list[0].id) // (.plugins.entries.mem9.config.agentName) // empty' openclaw.json 2>/dev/null)"
AGENT_FIELD=""
[ -n "$AGENT_ID" ] && AGENT_FIELD="-F agent_id=$AGENT_ID"
# Memory file
curl -sX POST "$API/imports" -H "X-API-Key: $API_KEY" $AGENT_FIELD -F "file=@memory.json" -F "file_type=memory"
# Session file
curl -sX POST "$API/imports" -H "X-API-Key: $API_KEY" $AGENT_FIELD -F "file=@session.json" -F "file_type=session" -F "session_id=ses-001"
# Check status
curl -s -H "X-API-Key: $API_KEY" "$API/imports"When presenting onboarding or recovery instructions:
Suggested English wording:
This API_KEY is not a nickname.
It is the key that reconnects you to your mem9 space.
It is also effectively your secret.
Never share it with anyone.
If someone else gets it, they can access your memory.
Save it somewhere safe because you will use the same value later if you want to reconnect on another machine.
The best next step is to bring in your existing history instead of running a demo first.
I can scan local files such as memory.json, memories/*.json, and sessions/*.json and import them into mem9.
Recovery plan:
1. Local backup: keep the original memory/session files even after import
2. Offsite recovery: save the API_KEY in a password manager, team vault, or another secure offsite location
3. New machine recovery: reinstall the plugin and configure the same API_KEY as `apiKey` in openclaw.json to reconnect to the same cloud memoryWhen user says "import memories to mem9" without specifying files:
Before uploading, read the agent id from the active openclaw.json config — using the same resolution order the plugin uses at runtime:
# agents.list[0].id is what the plugin receives as ctx.agentId at runtime.
# Falls back to plugins.entries.mem9.config.agentName (explicit plugin override).
AGENT_ID="$(jq -r '(.agents.list[0].id) // (.plugins.entries.mem9.config.agentName) // empty' openclaw.json 2>/dev/null)"
AGENT_FIELD=""
[ -n "$AGENT_ID" ] && AGENT_FIELD="-F agent_id=$AGENT_ID"Include -F "agent_id=$AGENT_ID" in each upload only when a value is found; omit it entirely otherwise.
Paths to scan:
./memory.json → file_type=memory
./memories.json → file_type=memory
./memories/*.json → file_type=memory
./sessions/*.json → file_type=session (session_id = filename)
./session/*.json → file_type=session (session_id = filename)| Symptom | Fix |
|---|---|
| Plugin not loading | Check slots.memory = "mem9" and entries.mem9.enabled = true |
| Plugin install hangs or fails on Alibaba Cloud / mainland China network | Re-run Step 2 and let it switch to NPM_CONFIG_REGISTRY=https://registry.npmmirror.com; verify curl -I https://registry.npmmirror.com/@mem9%2fmem9 succeeds |
404 on API call | Verify the saved API key was written into the plugin config; run curl https://api.mem9.ai/healthz |
| Existing API key unreachable | Re-check the value for typos; confirm network access to api.mem9.ai; if the key is lost, provision a new one via Step 1 |
After first read, do this immediately:
API_KEY reconnects the same cloud memory on a new machine.curl -s -H "X-API-Key: $API_KEY" "https://api.mem9.ai/v1alpha2/mem9s/memories?limit=10" | jq .memory_store / memory_search test only after import and recovery guidance are clear, or if the user explicitly asks for validation.Do not set up automatic daily self-updates for this skill.
Only update the local skill file when the user or maintainer explicitly asks for a refresh from a reviewed source.
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
░ stateless agents · cloud memory · zero amnesia ░
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in skills/mem9-ai of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Mem9 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Mem9 this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~5.9k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 10 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 35 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 297k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Skill CreatorAzure/azqr | 795 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 |
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Categories
Persistent cloud memory for OpenClaw agents. An agent skill from LeoYeAI/openclaw-master-skills. Mem9 is an agent skill from LeoYeAI/openclaw-master-skills. Persistent cloud memory for OpenClaw agents.
Mem9 fits situations like: agent Workflows work in your project.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill mem9 -a claude-code`. Or copy the skill folder (skills/mem9-ai in LeoYeAI/openclaw-master-skills) into .claude/skills/mem9 in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill mem9 -a codex`. Or copy the skill folder (skills/mem9-ai in LeoYeAI/openclaw-master-skills) into .agents/skills/mem9 in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --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.
Going by SKILL.md and its folder, Mem9 needs the command-line tools its instructions call (curl, jq and npm) and credentials named API_KEY. Our summary lists: A credential in API_KEY.
SKILL.md names 3 domains. In commands or code: api.mem9.ai, registry.npmmirror.com and registry.npmjs.org; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
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.
Mem9 is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.9k tokens (SKILL.md is roughly 24k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Mem9: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,160 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.