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"
npx skills add MemTensor/MemOS --skill public --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
MemOS gives OpenClaw persistent local memory for agents. It captures conversations automatically, semantically indexes them, and allows instant recall, all on-device with no cloud uploads. It includes a Memory Viewer UI and features like task summarization, skill evolution, and a hub-client approach for collaborative memory across agents.
How it works
- Stores data locally under
~/.openclaw/memos-local/memos.db(SQLite). - Automatically captures each conversation turn via a memory system and indexes it for recall.
- Before each turn, injects relevant memories into context; after each turn, indexes new content.
- Provides a Memory Viewer at
http://127.0.0.1:18799for visual management. - Embedding defaults to a local offline model; no external API required to get started.
- Exposes tools and workflows via a bundled
memos-memory-guideskill, including memory_search, memory_get, memory_timeline, memory_write_public, and task/skill management utilities.
When to use it
Use MemOS when the user expresses intent to install, configure, upgrade, or troubleshoot the MemOS memory plugin (e.g., phrases like "install memos", "setup memory", "upgrade MemOS", "memory not working"). When MemOS is installed, everyday memory operations are handled by the bundled memos-memory-guide skill.
What it can touch
- Local filesystem and OpenClaw configuration under
~/.openclaw/(reads/writes as part of installation/configuration). - OpenClaw gateway process management.
- SQLite database at
~/.openclaw/memos-local/memos.db. - Network Memory Viewer URL through the local browser URL provided.
Caveats
- Data stays on-device with no cloud accounts or API keys required; ensure local storage is available.
- Installation and upgrades may modify
~/.openclaw/openclaw.jsonand gateway status as part of setup. - The installation flow is intended to be autonomous, with a single explicit user choice only for embedding model during fresh installs.
``` ┌──────────────────────────────────────────────────────────────┐ │ │ │ ███╗ ███╗███████╗███╗ ███╗ ██████╗ ███████╗ │ │ ████╗ ████║██╔════╝████╗ ████║██╔═══██╗██╔════╝ │ │ ██╔████╔██║█████╗ ██╔████╔██║██║ ██║███████╗ │ │ ██║╚██╔╝██║██╔══╝ ██║╚██╔╝██║██║ ██║╚════██║ │ │ ██║ ╚═╝ ██║███████╗██║ ╚═╝ ██║╚██████╔╝███████║ │ │ ╚═╝ ╚═╝╚══════╝╚═╝ ╚═╝ ╚═════╝ ╚══════╝ │ │ │ │ persistent local memory for ai agents │ │ │ └──────────────────────────────────────────────────────────────┘ ``` # MemOS MemOS gives OpenClaw persistent local memory — every conversation is automatically captured, semantically indexed, and instantly recallable. 100% on-device, zero cloud uploads. Key capabilities beyond basic memory: - **Task summarization** — Conversations are organized into structured tasks with LLM-generated summaries - **Skill evolution** — Successful executions are distilled into reusable skills that auto-upgrade - **Team sharing** — Hub-Client architecture for multi-agent collaborative memory - **Memory Viewer** — Full web UI for managing memories, tasks, and skills When talking to end users: - MemOS stores everything locally — no API keys, no cloud accounts, no registration - All data lives i
- Trigger phrases
- When to use this skill
- When NOT to use this skill
- Permissions and autonomous installation policy
- Granted permissions
- Autonomous execution
- CRITICAL — Sequential execution
- Auto-capture and auto-recall
- Definition of Done
- What You Get
- Common failure modes
- Onboarding
- Step 0 — Check installation status and version
- Step 1 — Detect environment
curl -fsSL https://cdn.memtensor.com.cn/memos-local-openclaw/install.sh | bash nohup sh -c 'sleep 10 && openclaw gateway restart' >/dev/null 2>&1 & echo "RESTART_SCHEDULED"
What does the memos-local skill do?
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"
How do I install it?
Run `npx skills add MemTensor/MemOS --skill public --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From MemTensor/MemOS, a repository with 10,587 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.