Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/unvulcanised-watercress762/mem9npx agentmods add skills/unvulcanised-watercress762/mem9/betaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/unvulcanised-watercress762/mem9/beta)<a href="https://agentmods.dev/skills/unvulcanised-watercress762/mem9/beta"><img src="https://agentmods.dev/badge/skills/unvulcanised-watercress762/mem9/beta/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/unvulcanised-watercress762/mem9/beta"><img src="https://agentmods.dev/badge/skills/unvulcanised-watercress762/mem9/beta.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00063 | $0.05088 |
| Opus 5 | $0.00032 | $0.02544 |
| Sonnet 5 | $0.00013 | $0.01018 |
| Haiku 4.5 | $0.00006 | $0.00509 |
Grade B, and why
mem9 scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -sX PUT "$API/memories/{id}" -H "Content-Type: application/json" -d '{"content":"updated"}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf "https://api.mem9.ai/v1alpha1/mem9s/$SPACE_ID/memories?limit=1" \ How it starts
The opening of the file, as written. The whole thing — 587 lines — stays where its author put it; the contents beside it link to each section on GitHub.
┌──────────────────────────────────────────────────────────────┐
│ │
│ ███╗ ███╗███████╗███╗ ███╗ █████╗ │
│ ████╗ ████║██╔════╝████╗ ████║██╔══██╗ │
│ ██╔████╔██║█████╗ ██╔████╔██║╚██████║ │
│ ██║╚██╔╝██║██╔══╝ ██║╚██╔╝██║ ╚═══██║ │
│ ██║ ╚═╝ ██║███████╗██║ ╚═╝ ██║ █████╔╝ │
│ ╚═╝ ╚═╝╚══════╝╚═╝ ╚═╝ ╚════╝ │
│ │
│ persistent memory for ai agents │
│ │
└──────────────────────────────────────────────────────────────┘
mem9
mem9 gives OpenClaw persistent memory across resets, restarts, and new machines.
The plugin connects to one cloud memory space, identified by a space ID.
When talking to end users:
- Say "space ID", "memory space", or "cloud memory space"
- Do not mention
tenantIDunless you are editing raw plugin config - Explain that the space ID is what reconnects the user to the same mem9 space
- Treat the space ID as something the user should save for reconnecting later
- Clearly warn that the space ID is effectively a secret and must never be shared
Trigger phrases
Use this skill when the user expresses intent to store, recall, or manage long-term memory.
Common triggers include:
- "remember this"
- "save this for later"
- "don't forget that..."
- "what did I say last time?"
- "recall my preferences"
- "forget that"
When to use this skill
Use this skill when the user wants OpenClaw to persist or manage long-term memory across sessions, devices, or restarts.
Typical situations include:
- The user asks OpenClaw to remember something for future sessions
- The user wants to recall or reconnect to existing long-term memory
- The user wants persistent memory instead of local/session-only memory
- The user wants to import existing OpenClaw memory files into mem9
- The user is moving to a new machine and wants to keep the same memory
- The user wants multiple agents or workflows to share the same memory space
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 587 lines · 63 tokens per session scan B ac98bc3d7b21
mem9 is a skill published in the GitHub repository unvulcanised-watercress762/mem9 (3 stars, last pushed today), licensed Apache-2.0. It adds 63 tokens to every session and 5,088 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
memos-local
Persistent local memory for OpenClaw agents. Use when users say: "install memos" "install MemOS" "setup memory" "add memory plugin" "openclaw memory" "memos onboarding" "memory not working" "configure memory" "enable memory" "upgrade MemOS" "update memory plugin".
mem9
Persistent cloud memory plugin for OpenClaw. This document routes setup, troubleshooting, and uninstall flows and defines config boundaries.
memory-write
Captures a durable fact to project memory through the kit's safe write path (PoisonGuard secret/injection screening + home-path sanitization + dedup + conflict detection) — preferring the cmk MCP tools (mkremember / mkforget / mktrust) when connected, falling back to the cmk CLI. Use when the user says "remember…
bootstrap
Scaffolds the core-memory-kit directory structure (context/, scripts/, cron/jobs/) into the current project. Idempotent — never overwrites existing files. Run once per project after installing the plugin. Use when the user says "bootstrap the memory system", "set up memory here", or "scaffold the memory kit".
troubleshooting
Diagnoses and repairs core-memory-kit itself when the memory system is broken — the per-failure-code repair book. Fire whenever a "⚠ [core-memory-kit]" whisper appears on the prompt (it names the failure and points here), or when the user reports a kit symptom however they phrase it: memory is not being saved, nothing…
memory-search
Searches the project's recorded memory (core-memory-kit) — decisions, conventions, architecture, the reasoning behind choices, and where things live — and returns a curated, cited summary. Fire whenever the answer might be something the project already established in past work, HOWEVER the question is phrased — any…