Does memos auto-invoke its skills?

Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Data

Plugin

memos

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

FLOW.md

memtensor@memtensor

GitHub

Plugin Signal81/100Strong

maintained99

capable46

documented100

adopted86

Install

$ npx -y skills add MemTensor/MemOS --agent claude-code

Run the curl in your terminal, the rest in Claude Code.

Stats

Python TypeScript JavaScript Node Bash

+6 tags

PowerShell SQLite Docker Linux Git GitHub

10,658

Stars

987

Forks

Active

Maintenance

TypeScript

Language

Apache-2.0

License

2d ago

Last commit

1y ago

Created

Repo: MemTensor/MemOS

In this plugin

5 agents 3 skills

agents
skills

See everything inside

What's inside

Skills

/ask-user-questionAsk users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them./dev-browserBrowser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot",/safe-file-deletionEnforces explicit user permission before any file deletion. Activates when you're about to use rm, unlink, fs.rm, or any operation that removes files from disk. MUST be followed for all delete operations.

Agents

backend-devMemOS backend / library implementation sub-agent. Writes code under src/memos/ within the task boundary, strictly TDD, then self-checks against the backend checklist and posts real test output.code-reviewerCode-review sub-agent. Reviews MemOS diffs for contract consistency, Ruff / typing / optional-dependency handling, and test evidence; returns APPROVE or CHANGES_REQUESTED.design-reviewerDesign-review sub-agent. Reviews design docs across the four dimensions of architecture, interface, performance, and security, covering MemOS's multi-memory / multi-storage backend constraints.explorerRead-only code exploration sub-agent. Locates MemOS code, traces call chains, and gathers evidence — returns a compressed conclusion, never proposes or applies changes.integration-testerMemOS integration-testing sub-agent. Authors and executes pytest cases under tests/ based on the task's requirements and design, and emits real test reports.

Badges

README

Read on GitHub

👾 MemOS: Memory Operating System for LLM & AI Agents

MemOS is a Memory Operating System for LLMs and AI agents that unifies store / retrieve / manage for long-term memory, enabling context-aware and personalized interactions with KB, multi-modal, tool memory, and enterprise-grade optimizations built in.

Key Features

Unified Memory API: A single API to add, retrieve, edit, and delete memory—structured as a graph, inspectable and editable by design, not a black-box embedding store.
Multi-Modal Memory: Natively supports text, images, tool traces, and personas, retrieved and reasoned together in one memory system.
Multi-Cube Knowledge Base Management: Manage multiple knowledge bases as composable memory cubes, enabling isolation, controlled sharing, and dynamic composition across users, projects, and agents.
Asynchronous Ingestion via MemScheduler: Run memory operations asynchronously with millisecond-level latency for production stability under high concurrency.
Memory Feedback & Correction: Refine memory with natural-language feedback—correcting, supplementing, or replacing existing memories over time.

News

2026-07-02 · 🏆 MemOS Advances Agent and User Memory Benchmarks With MemOS, OpenClaw improves average task completion from 36.63% to 50.87% across five agent tasks. MemOS also achieves 88.83 on LoCoMo and 89.20 on LongMemEval, and leads in OmniMemEval, a unified evaluation of 14 commercial memory products across ten datasets.
2026-05-09 · 🧠 memos-local-plugin 2.0 Official local memory plugin for Hermes Agent and OpenClaw. One core powers self-evolving memory across L1 traces, L2 policies, L3 world models, and crystallized Skills, with local-first storage and feedback-driven retrieval.
2026-04-10 · 👧🏻 MemOS Hermes Agent Local Plugin Official Hermes Agent memory plugins launched: Hybrid retrieval (FTS5 + vector), smart dedup, tiered skill evolution, multi-agent collaboration. 100% local, zero cloud dependency.
2026-03-08 · 🦞 MemOS OpenClaw Plugin — Cloud & Local Official OpenClaw memory plugins launched. Cloud Plugin: hosted memory service with 72% lower token usage and multi-agent memory sharing (MemOS-Cloud-OpenClaw-Plugin). Local Plugin (v1.0.0): 100% on-device memory with persistent SQLite, hybrid search (FTS5 + vector), task summarization & skill evolution, multi-agent collaboration, and a full Memory Viewer dashboard.

📊 Performance

MemOS leads across multiple benchmarks — evaluated against mainstream commercial memory products across 5 user memory and 5 agent memory tasks.

Benchmark	Score
LoCoMo	88.83
LongMemEval	89.20
PersonaMem v2	40.58
HaluMem	80.91
BEAM-10M	56.75
GDPVal	62.07
LiveCodeBench	64.96
OmniMath	61.00
SWE-Bench	38.46
BrowseComp-Plus	23.85

Evaluated via OmniMemEval — https://github.com/MemTensor/OmniMemEval.

🎯 What MemOS Is For

MemOS gives AI agents long-term memory. Common uses:

AI assistants with consistent, context-rich conversations
Customer support that recalls past tickets and user history
Personalized agents that adapt to individual preferences
Multi-agent collaboration with shared or isolated memory

🚀 Quick Start

MemOS is built around four entry points. Pick the one that matches your scenario.

	Cloud API	Self-Host	OpenClaw Cloud Plugin	Local Plugin
Best for	Your app, fully managed	Teams on own infra	OpenClaw users, zero ops	Hermes/OpenClaw, 100% on-device
Setup	Get an API key	docker compose up	openclaw plugins install	npm install + config
Infra needed	None (hosted)	Neo4j + Qdrant	None (uses MemOS Cloud)	None (local SQLite)
Data lives	MemOS Cloud	Your servers	MemOS Cloud	Your machine

☁️ Use the Cloud API (Hosted)

You want to add memory to your app through a fully managed service — no infrastructure to run.

1. Get an API key:

Sign up on the MemOS dashboard.
Go to API Keys and copy your key (starts with mpg-). Keep it server-side.

2. Add and search memories:

import requests

API_KEY = "mpg-..."                  # keep this server-side
base = "https://memos.memtensor.cn/api/openmem/v1"
headers = {"Authorization": f"Token {API_KEY}", "Content-Type": "application/json"}

# 1. Add a memory
requests.post(f"{base}/add/message", headers=headers, json={
    "user_id": "alice",
    "conversation_id": "conv_001",
    "messages": [{"role": "user", "content": "I like strawberry"}],
})

# 2. Search memories
res = requests.post(f"{base}/search/memory", headers=headers, json={
    "query": "What do I like?",
    "user_id": "alice",
})
print(res.json())

Next steps:

MemOS Cloud Getting Started — connect to MemOS Cloud and enable memory in minutes.
MemOS Cloud Platform — explore the Cloud dashboard, features, and workflows.

🖥️ Self-Host the MemOS Service

You want to run MemOS as a REST service on your own machine or cluster.

Option A — Docker (recommended):

git clone https://github.com/MemTensor/MemOS.git
cd MemOS
cp docker/.env.example .env          # fill in your API keys in .env
cd docker
docker compose up                    # starts MemOS API + Neo4j + Qdrant

The API is served at http://localhost:8000.

Option B — Run with uvicorn (without Docker):

git clone https://github.com/MemTensor/MemOS.git
cd MemOS
cp docker/.env.example .env          # fill in your API keys in .env
# Ensure Neo4j and Qdrant are running, then:
cd src
uvicorn memos.api.server_api:app --host 0.0.0.0 --port 8000 --workers 1

See [docker/.env.example](./docker/.env.example) for all configuration options (LLM provider, embedder, vector DB, graph DB, scheduler). The full deployment guide is at https://memos-docs.openmem.net/open_source/getting_started/rest_api_server/.

Try the API:

import requests, json

headers = {"Content-Type": "application/json"}
base = "http://localhost:8000/product"

# 1. Create a memory cube
requests.post(f"{base}/create_cube", headers=headers, data=json.dumps({
    "cube_name": "Alice's memory",
    "owner_id": "alice",
    "cube_id": "alice_cube",
}))

# 2. Add a memory
requests.post(f"{base}/add", headers=headers, data=json.dumps({
    "user_id": "alice",
    "writable_cube_ids": ["alice_cube"],
    "messages": [{"role": "user", "content": "I like strawberry"}],
    "async_mode": "sync",
}))

# 3. Search memories
res = requests.post(f"{base}/search", headers=headers, data=json.dumps({
    "query": "What do I like?",
    "user_id": "alice",
    "readable_cube_ids": ["alice_cube"],
}))
print(res.json())

🧠 MemOS Plugin: Persistent Memory for Your AI Agents ✨

Your OpenClaw and Hermes Agents now have the best memory system — choose Cloud Service or Self-hosted to get started 🏃🏻

🔌 Plugin	💡 Core Features	🧩 Resources
🧠 memos-local-plugin 2.0		🌐 Website · 📖 Docs · 🐙 GitHub · 📦 NPM
☁️ OpenClaw Cloud Plugin		🖥️ MemOS Dashboard · 📖 Full Tutorial

1. OpenClaw Cloud Plugin

You use OpenClaw and want persistent memory via MemOS Cloud — no infrastructure to run.

Repo: MemTensor/MemOS · apps/MemOS-Cloud-OpenClaw-Plugin
NPM: [@memtensor/memos-cloud-openclaw-plugin](https://www.npmjs.com/package/@memtensor/memos-cloud-openclaw-plugin)
Dashboard: https://memos-dashboard.openmem.net/
Tutorial: https://memos-docs.openmem.net/openclaw/guide

Install:

openclaw plugins install @memtensor/memos-cloud-openclaw-plugin@latest
openclaw gateway restart

The plugin recalls memories from MemOS Cloud before each agent run and saves new messages back after the run ends.

2. Local Plugin (memos-local-plugin 2.0)

You use Hermes Agent or OpenClaw and want 100% on-device memory — nothing leaves your machine.

Repo: MemTensor/MemOS · apps/memos-local-plugin
NPM: [@memtensor/memos-local-plugin](https://www.npmjs.com/package/@memtensor/memos-local-plugin)
Docs: https://memos-docs.openmem.net/cn/openclaw/local_plugin
Viewer dashboard: see apps/memos-local-plugin/viewer/

Install (macOS / Linux):

curl -fsSL https://raw.githubusercontent.com/MemTensor/MemOS/main/apps/memos-local-plugin/install.sh | bash

Install (Windows PowerShell):

irm https://raw.githubusercontent.com/MemTensor/MemOS/main/apps/memos-local-plugin/install.ps1 -OutFile "$env:TEMP\memos-install.ps1"; powershell -ExecutionPolicy Bypass -File "$env:TEMP\memos-install.ps1"

Requires Node.js and an already-installed OpenClaw or Hermes. The installer auto-detects OpenClaw and Hermes, deploys the plugin to the right agent home (~/.hermes/plugins/ or ~/.openclaw/plugins/), writes the initial config.yaml, and restarts the agent runtime.

Features: hybrid retrieval (FTS5 + vector), smart dedup, tiered skill evolution (L1 traces / L2 policies / L3 world model), multi-agent collaboration, local-first SQLite storage.

🤝 Community

GitHub Issues: https://github.com/MemTensor/MemOS/issues
GitHub Discussions: https://github.com/MemTensor/MemOS/discussions
Discord: https://discord.gg/Txbx3gebZR
WeChat: scan the QR code to join the group.

📚 Citation

If you use MemOS in your research, please cite:

@article{li2025memos_long,
  title={MemOS: A Memory OS for AI System},
  author={Li, Zhiyu and Song, Shichao and Xi, Chenyang and Wang, Hanyu and Tang, Chen and Niu, Simin and Chen, Ding and Yang, Jiawei and Li, Chunyu and Yu, Qingchen and Zhao, Jihao and Wang, Yezhaohui and Liu, Peng and Lin, Zehao and Wang, Pengyuan and Huo, Jiahao and Chen, Tianyi and Chen, Kai and Li, Kehang and Tao, Zhen and Ren, Junpeng and Lai, Huayi and Wu, Hao and Tang, Bo and Wang, Zhenren and Fan, Zhaoxin and Zhang, Ningyu and Zhang, Linfeng and Yan, Junchi and Yang, Mingchuan and Xu, Tong and Xu, Wei and Chen, Huajun and Wang, Haofeng and Yang, Hongkang and Zhang, Wentao and Xu, Zhi-Qin John and Chen, Siheng and Xiong, Feiyu},
  journal={arXiv preprint arXiv:2507.03724},
  year={2025},
  url={https://arxiv.org/abs/2507.03724}
}

@article{li2025memos_short,
  title={MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models},
  author={Li, Zhiyu and Song, Shichao and Wang, Hanyu and Niu, Simin and Chen, Ding and Yang, Jiawei and Xi, Chenyang and Lai, Huayi and Zhao, Jihao and Wang, Yezhaohui and others},
  journal={arXiv preprint arXiv:2505.22101},
  year={2025},
  url={https://arxiv.org/abs/2505.22101}
}

⚖️ License

MemOS is licensed under the Apache 2.0 License.

File tree

1647

MemTensor/MemOSView on GitHub

.claude/
  agents/
    backend-dev.md
    code-reviewer.md
    design-reviewer.md
    explorer.md
    integration-tester.md
.codex/
  agents/
    backend-dev.toml
    code-reviewer.toml
    design-reviewer.toml
    explorer.toml
    integration-tester.toml
.github/
  ISSUE_TEMPLATE/
    bug-report.yml
    config.yml
    feature-request.yml
  PULL_REQUEST_TEMPLATE.md
  scripts/
    append-local-plugin-release-intent.mjs
    append-local-plugin-release-intent.test.mjs
    audit-local-plugin-package.mjs
    audit-local-plugin-package.test.mjs
    create-local-plugin-github-release.mjs
    create-local-plugin-github-release.test.mjs
    draft-local-plugin-release-notes.mjs
    draft-local-plugin-release-notes.test.mjs
    inspect-local-plugin-release-state.mjs
    inspect-local-plugin-release-state.test.mjs
    local-plugin-release-contract.mjs
    local-plugin-release-contract.test.mjs
    prepare-memos-release.mjs
    prepare-memos-release.test.mjs
    publish-local-plugin.sh
    publish-local-plugin.test.mjs
    publish-paired-local-plugin-release.mjs
    publish-paired-local-plugin-release.test.mjs
    retry.sh
    wait-for-local-plugin-npm-release.mjs
    wait-for-local-plugin-npm-release.test.mjs
  workflows/
    memos-local-plugin-post-merge-dry-run.yml
    memos-local-plugin-publish.yml
    memos-release-post-merge-dry-run.yml
    memos-release-pre-merge-dry-run.yml
    memos-release-publish-paired-local-plugin.yml
    memos-release-publish.yml
    openclaw-plugin-publish.yml
    python-release.yml
    python-tests.yml
    stale.yml
    yunxiao-github-sync.yml
.gitignore
.pre-commit-config.yaml
AGENTS.md
apps/
  MemOS-Cloud-OpenClaw-Plugin/
    .gitignore
    clawdbot.plugin.json
    HOOK.md
    index.js
    lib/
      arms-reporter.js
      check-update.js
      config-resolution-schema.js
      config-ui/
      config-ui-server.js
        app.css
        app.js
        icon.svg
        index.html
      memos-cloud-api.js
    LICENSE
    moltbot.plugin.json
    openclaw.plugin.json
    package.json
    README_ZH.md
    README.md
    scripts/
      sync-version.js
    test/
      direct-session-user-id.test.mjs
      query-strip.test.mjs
  memos-local-openclaw/
    .env.example
    .gitignore
    demo-guide.html
    docs/
      index.html
      troubleshooting.html
    HUB-SHARING-GUIDE.md
    index.ts
    install.ps1
    install.sh
    openclaw.plugin.json
    package.json
    plugin-impl.ts
    README.md
    scripts/
      e2e-hub-test.ts
      generate-telemetry-credentials.cjs
      mock-skills.ts
      native-binding.cjs
      postinstall.cjs
      re-embed.ts
      refresh-skill.ts
      refresh-summaries.ts
      run-accuracy-test.ts
      seed-test-data.ts
      smoke-test.ts
      start-viewer.ts
      test-agent-isolation.ts
    site/
      public/
        SKILL.md
    skill/
      browserwing-admin/
        SKILL.md
      browserwing-executor/
        SKILL.md
      memos-memory-guide/
        SKILL.md
    src/
      capture/
        index.ts
      client/
        connector.ts
        hub.ts
        skill-sync.ts
      config.ts
      embedding/
        index.ts
        local.ts
        providers/
          cohere.ts
          gemini.ts
          mistral.ts
          openai.ts
          voyage.ts
      hub/
        auth.ts
        server.ts
        user-manager.ts
      index.ts
      ingest/
        chunker.ts
        dedup.ts
        providers/
          anthropic.ts
          bedrock.ts
          gemini.ts
          index.ts
          openai.ts
        task-processor.ts
        worker.ts
      openclaw-api.ts
      openclaw-config.ts
      path-utils.ts
      recall/
        engine.ts
        mmr.ts
        recency.ts
        rrf.ts
        session-policy.ts
      shared/
        json5.ts
        llm-call.ts
        openclaw-config.ts
        openrouter.ts
      sharing/
        types.contract.ts
        types.ts
      skill/
        __tests__/
          evolver.test.ts
        bundled-memory-guide.ts
        evaluator.ts
        evolver.ts
        generator.ts
        installer.ts
        upgrader.ts
        validator.ts
      storage/
        ensure-binding.ts
        sqlite.ts
        vector.ts
      telemetry.ts
      tools/
        index.ts
        memory-get.ts
        memory-search.ts
        memory-timeline.ts
        network-memory-detail.ts
      types.ts
      update-check.ts
      viewer/
        html.ts
        server.ts
    tests/
      accuracy.test.ts
      auto-recall-cron-gate.test.ts
      bench/
        README.md
      capture.test.ts
      chunker.test.ts
      client-connector.test.ts
      config.test.ts
      cross-session-memory.test.ts
      e2e-capabilities-fallback.ts
      e2e-host-model-proxy.ts
      e2e-summarizer-skill.ts
      embedding-input-type.test.ts
      embedding-memory-leak.test.ts
      embedding-reembed.test.ts
      esm-module-format.test.ts
      gemini-viewer-test.test.ts
      hub-auth.test.ts
      hub-eager-connect.test.ts
      hub-server.test.ts
      incremental-sharing.test.ts
      integration.test.ts
      issue-1559-memory-api-migration.test.ts
      json5-config.test.ts
      llm-call.test.ts
      memory-registration-api.test.ts
      memory-search-tool.test.ts
      migration-status.test.ts
      module-format.test.ts
      multi-agent.test.ts
      normalize-auto-recall-query.test.ts
      openclaw-config-patch.test.ts
      openclaw-config.test.ts
      openclaw-fallback.test.ts
      package-manifest.test.ts
      path-utils.test.ts
      plugin-impl-access.test.ts
      plugin-openclaw-wiring.test.ts
      policy.test.ts
      postinstall-native-binding.test.ts
      recall-engine-exclude-session.test.ts
      recall.test.ts
      session-policy.test.ts
      shutdown-lifecycle.test.ts
      skill-auto-install.test.ts
      skill-prompt-policy.test.ts
      skill-runtime-flow.test.ts
      skill-sync.test.ts
      skill-v1-enhancements.test.ts
      startup-registration.test.ts
      storage.test.ts
      task-processor.test.ts
      topic-classifier-dispatch.test.ts
      topic-judge-minimax-1315.test.ts
      update-install.test.ts
      verify-npm-package.sh
      viewer-config.test.ts
      viewer-env-resolution.test.ts
      viewer-search-params.test.ts
      viewer-sharing.test.ts
      viewer-ui.test.ts
      worker-lifecycle.test.ts
    tsconfig.json
    types/
      openclaw__plugin-sdk/
        index.d.ts
    vitest.config.ts
    www/
      demo/
        index.html
      docs/
        index.html
        troubleshooting.html
      index.html
  memos-local-plugin/
    .gitignore
    .npmignore
    adapters/
      ALGORITHMS.md
      hermes/
        install.hermes.sh
        memos_provider/
          __init__.py
          .gitkeep
          bridge_client.py
          daemon_manager.py
          runtime_home.py
          shared_bridge_runtime.py
        plugin.yaml
        README.md
      openclaw/
        .gitkeep
        bridge.ts
        index.ts
        install.openclaw.sh
        openclaw-api.ts
        README.md
        runtime-lock.ts
        tools.ts
      README.md
    agent-contract/
      .gitkeep
      dto.ts
      episode-status.ts
      errors.ts
      events.ts
      jsonrpc.ts
      log-record.ts
      memory-core.ts
      README.md
    ARCHITECTURE.md
    bridge/
    bridge.cts
    bridge.mts
      .gitkeep
      hermes-process.ts
      methods.ts
      README.md
      stdio.ts
    CHANGELOG.md
    core/
      capture/
        .gitkeep
        ALGORITHMS.md
        alpha-scorer.ts
        batch-scorer.ts
        capture.ts
        embedder.ts
        error-signature.ts
        events.ts
        index.ts
        normalizer.ts
        README.md
        reflection-extractor.ts
        reflection-synth.ts
        step-extractor.ts
        subscriber.ts
        summarizer.ts
        tagger.ts
        types.ts
      config/
        .gitkeep
        defaults.ts
        index.ts
        migrations.ts
        paths.ts
        README.md
        schema.ts
        writer.ts
        yaml.ts
      embedding/
        cache.ts
        embedder.ts
        fetcher.ts
        index.ts
        normalize.ts
        providers/
          .gitkeep
          cohere.ts
          gemini.ts
          local.ts
          mistral.ts
          openai.ts
          voyage.ts
        README.md
        retry-worker.ts
        types.ts
      episode/
        .gitkeep
        README.md
      experience/
        feedback-builder.ts
        feedback-refiner.ts
      feedback/
        .gitkeep
        ALGORITHMS.md
        classifier.ts
        events.ts
        evidence.ts
        feedback.ts
        index.ts
        llm-classifier.ts
        README.md
        signals.ts
        subscriber.ts
        synthesize.ts
        types.ts
      hub/
        .gitkeep
        auth.ts
        client.ts
        README.md
        runtime.ts
        server.ts
      id.ts
      index.ts
      injection/
        scheduler.ts
      llm/
... 1600 more

Showing a partial view of a very large repo.

More Flows by @memtensor.

VerifiedPlugin

Development

skills-vote

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

2 skills

@memtensor

View Plugin

FAQ

memos is a Claude Code plugin with 3 hand-picked skills for data work, indexed on Flowy. Install it with the command on its page. It includes ask-user-question, dev-browser, safe-file-deletion. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

What is memos?: Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
How do I install memos?: Run these in Claude Code: npx -y skills add MemTensor/MemOS --agent claude-code. Then prompt normally.
Does memos auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is memos free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.