mem9 is a persistent memory service for AI agents that preserves information across sessions and machines and can share it among multiple agents. It is used with OpenClaw, coding agents, workflow platforms, and custom clients that need shared storage and recall. The catalogue add-ons connect agents and workflows to mem9 memory.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/mem9-ai/mem9/publicnpx skills add mem9-ai/mem9 --skill publicgit clone --depth 1 https://github.com/mem9-ai/mem9Wrote 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/mem9-ai/mem9/public)<a href="https://agentmods.dev/skills/mem9-ai/mem9/public"><img src="https://agentmods.dev/badge/skills/mem9-ai/mem9/public.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.01297 |
| Opus 5 | $0.00014 | $0.00648 |
| Sonnet 5 | $0.00005 | $0.00259 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
mem9 scanned grade A with 0 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 6d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 remoteSKILL.mdURL through the create-new setup flow and first restart. - Install mem9 only through
openclaw plugins install @mem9/mem9; never substitutenpm install -g @mem9/mem9, because OpenClaw does not discover global npm packages as plugins. - Prevent invalid compatibility fallbacks: never write
plugins.entries.mem9.apiKey; onlyplugins.entries.mem9.config.apiKeyis valid. - Configure OpenClaw 4.23+ hook permission with
plugins.entries.mem9.hooks.allowConversationAccess = trueso mem9 can read conversation messages duringagent_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.mdin that same resumed turn; never ask for repeatedhimessages. - In create-new mode, do not treat missing
plugins.entries.mem9.config.apiKeyas 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.
What ships with it
19 files 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.
- _meta.json 123 B
- favicon.svg 908 B
- logo.png 1240 KB
- mem9-github-square.png 19 KB
- mem9-github-square.svg 533 B
- mem9-mark.svg 1.7 KB
- mem9-wordmark-dark-square.png 109 KB
- mem9-wordmark-dark-square.svg 2.3 KB
- mem9-wordmark-square.png 39 KB
- mem9-wordmark-square.svg 2.3 KB
- mem9-wordmark.png 45 KB
- mem9-wordmark.svg 2.2 KB
- qr-code-install-mem9.png 3.5 KB
- release-notes-hero.jpg 185 KB
- SETUP.md 12 KB
- tidb-logo.png 20 KB
- tidb-logo.svg 1.6 KB
- TROUBLESHOOTING.md 17 KB
- UNINSTALL.md 11 KB
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.
- 6d ago First seen · 71 lines · 27 tokens per session scan A 01f49c7c9e12
mem9 is a skill published in the GitHub repository mem9-ai/mem9 (1,205 stars, last pushed 12d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,297 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mem9
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".
mem9
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".
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".
j-space
Use this skill to establish and operate the model's inner workspace — the J-space — for any task that needs more than fluent output: multi-step or chained reasoning, planning, long-horizon and agentic work, competition-level problems, complex debugging, keeping many parts of a deliverable globally consistent, holding…
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…
openviking-context-database
Use OpenViking from OpenClaw through @openviking/openclaw-plugin: long-term memory, session archives, resource and Agent Skill import, semantic recall, recall trace debugging, and externalized tool-result recovery. Prefer this skill when the user wants to use, query, debug, or operate OpenViking context from an…