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
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add mem9-ai/mem9/plugin install claude-pluginWrote 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/recall)<a href="https://agentmods.dev/skills/mem9-ai/mem9/recall"><img src="https://agentmods.dev/badge/skills/mem9-ai/mem9/recall.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 | $0.00012 | $0.00556 |
| Opus 5 | $0.00006 | $0.00278 |
| Sonnet 5 | $0.00002 | $0.00111 |
| Haiku 4.5 | $0.00001 | $0.00056 |
Grade A, and why
recall scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf --max-time 8 \ What it actually says
Mem9 Recall
Use this skill when the current request could benefit from historical context stored in Mem9.
Steps
- Check
${CLAUDE_PLUGIN_DATA}/auth.json. If it is missing, tell the user to run/mem9:setupfirst. - Use
${CLAUDE_PLUGIN_DATA}/auth.jsononly as request credentials. Do not print the file contents or the API key. - Search Mem9 with the current question across all agents in the account (no
agent_idfilter).
set -euo pipefail
auth_file="${CLAUDE_PLUGIN_DATA}/auth.json"
test -f "$auth_file"
read_api_key_and_base_url="$(node -e 'const fs=require("node:fs"); const data=JSON.parse(fs.readFileSync(process.argv[1],"utf8")); const values=[data.api_key || "", data.base_url || "https://api.mem9.ai"]; process.stdout.write(values.join("\t"));' "$auth_file")"
api_key="${read_api_key_and_base_url%% *}"
base_url="${read_api_key_and_base_url#* }"
test -n "$api_key"
test -n "$base_url"
plugin_version="unknown"
if [ -n "${CLAUDE_PLUGIN_ROOT:-}" ] && [ -f "${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json" ]; then
plugin_version="$(node -e 'const fs=require("node:fs"); const data=JSON.parse(fs.readFileSync(process.argv[1],"utf8")); process.stdout.write(data.version || "unknown");' "${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json")"
fi
query='REPLACE_WITH_SEARCH_QUERY'
encoded_query="$(printf '%s' "$query" | node -e 'const fs=require("node:fs"); const raw=fs.readFileSync(0,"utf8").trim(); process.stdout.write(encodeURIComponent(raw));')"
curl -sf --max-time 8 \
-H "Content-Type: application/json" \
-H "X-API-Key: ${api_key}" \
-H "X-Mnemo-Agent-Id: claude-code" \
-H "User-Agent: mem9-plugin/claude-code/${plugin_version}" \
"${base_url%/}/v1alpha2/mem9s/memories?q=${encoded_query}&limit=10"
Return only the memories that help with the current question. Never reveal secret values.
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.
- 7d ago First seen · 47 lines · 12 tokens per session scan A 835c3e63d56d
recall is a skill published in the GitHub repository mem9-ai/mem9 (1,205 stars, last pushed 12d ago), licensed Apache-2.0. It adds 12 tokens to every session and 556 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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…
ov-experience-memory
Retrieve and apply OpenViking Experience memories through the Agent runtime's generic OpenViking search and read tools. Use before or during executable, multi-step, or tool-based work such as coding, file or data changes, configuration, deployment, workflow execution, and failure recovery when prior operational…
openviking-memory
Recall and persist long-term memory through the OpenViking MCP tools. Use at the start of any substantive task (coding, configuration, debugging, multi-step or tool-based work) to retrieve relevant prior knowledge with find/search/read, and during or after work to persist durable facts, preferences, decisions, and…
experience_loader
Load relevant OpenViking experience memories via case-linked experience candidates before solving a task.