MemOS OpenClaw 插件MemOS OpenClaw Plugin

MemOS

为 OpenClaw 提供完全本地化的持久记忆、智能任务总结、技能自动进化和多智能体协同。npm 一键安装，支持分级模型配置。 Fully local persistent memory, smart task summarization, auto skill evolution, and multi-agent collaboration for OpenClaw. One-command install, tiered model support.

系统架构Architecture

四条流水线：记忆写入 → 任务总结与技能进化（异步）→ 智能检索 → 协同共享。每个 Agent 拥有独立记忆空间，通过公共记忆和技能共享实现协同进化。Four pipelines: write → task & skill evolution (async) → retrieval → collaboration. Each agent has isolated memory; public memory and skill sharing enable collective evolution.

数据流Data Flow

写入Write

1. agent_end → Capture → Chunk → LLM Summary → Embed → Dedup → Store
2. 异步：任务检测 → 任务摘要 → 技能评估 → 技能生成/升级Async: task detect → summary → skill eval → create/upgrade

检索Read

1. 每轮自动：before_agent_start 用用户消息检索 → LLM 过滤相关 → 注入 system 上下文；无结果时提示 agent 自生成 query 调 memory_search。Per turn: before_agent_start searches with user message → LLM filters relevant → inject system context; if no hits, hint agent to call memory_search with self-generated query.
2. memory_search → FTS5+Vector → RRF → MMR → Decay → LLM filter → excerpts + chunkId/task_id（无 summary）
3. task_summary / skill_get(skillId|taskId) / memory_timeline(chunkId) / skill_install

快速开始Quick Start

• Node.js ≥ 18
• OpenClaw 已安装OpenClaw installed
• Embedding / Summarizer API 可选，不配自动用本地模型Embedding / Summarizer APIs optional, falls back to local

openclaw plugins install @memtensor/memos-local-openclaw-plugin
openclaw gateway startbash

升级Upgrade

openclaw plugins update memos-local-openclaw-plugin
openclaw gateway stop && openclaw gateway startbash

配置Configuration

两种方式：编辑 openclaw.json 或通过 Viewer 网页面板在线修改。支持分级模型。Two methods: edit openclaw.json or via Viewer web panel. Tiered models supported.

{
  "plugins": {
    "slots": { "memory": "memos-local" },
    "entries": { "memos-local": {
      "config": {
        "embedding": {                           // lightweight
          "provider": "openai_compatible",
          "model": "bge-m3",
          "endpoint": "https://your-api-endpoint/v1",
          "apiKey": "sk-••••••"
        },
        "summarizer": {                          // mid-tier
            "provider": "openai_compatible",
          "model": "gpt-4o-mini",
          "endpoint": "https://your-api-endpoint/v1",
          "apiKey": "sk-••••••"
        },
        "skillEvolution": {
          "summarizer": {                        // high-quality
            "provider": "openai_compatible",
            "model": "claude-4.6-opus",
            "endpoint": "https://your-api-endpoint/v1",
            "apiKey": "sk-••••••"
          }
        },
        "recall": {                               // optional
          "vectorSearchMaxChunks": 0   // 0=search all; set 200000–300000 only if slow on huge DB
        },
        "viewerPort": 18799
      }
    }}
  }
}json

🦐 记忆迁移 — 再续前缘🦐 Memory Migration — Reconnect

将 OpenClaw 原生内置的记忆数据（SQLite 存储的对话历史）无缝迁移到 MemOS 的智能记忆系统。你和 AI 共同积累的每一段对话，都值得被记住。Seamlessly migrate OpenClaw's native built-in memory data (SQLite conversation history) to MemOS's intelligent memory system. Every conversation you've built with AI deserves to be remembered.

操作步骤Usage

方式一：通过 Viewer 网页面板（推荐）Method 1: Via Viewer Web Panel (Recommended)

1. 访问 http://127.0.0.1:18799，切换到 Import 页面。Visit http://127.0.0.1:18799, switch to the Import page.
2. 点击 扫描 OpenClaw 原生记忆，系统自动扫描 ~/.openclaw/ 下的 SQLite 数据库和 JSONL 日志。Click Scan OpenClaw Native Memories — the system auto-scans SQLite databases and JSONL logs under ~/.openclaw/.
3. 查看扫描结果（文件数、会话数、消息数），确认后点击 开始导入。Review scan results (files, sessions, messages), then click Start Import.
4. 实时查看导入进度条、统计数据（已导入/跳过/合并/错误）和日志。Monitor real-time progress bar, stats (stored/skipped/merged/errors), and logs.

方式二：通过 Agent 对话Method 2: Via Agent Chat

在与 OpenClaw 的对话中，直接让 AI 操作：In your conversation with OpenClaw, tell the AI:

// Example prompts
"请帮我导入 OpenClaw 的原生记忆"
"Import my OpenClaw native memories"text

方式三：通过 HTTP APIMethod 3: Via HTTP API

# 1. 扫描
curl http://127.0.0.1:18799/api/migrate/scan

# 2. 开始导入（SSE 流式进度）
curl http://127.0.0.1:18799/api/migrate/start

# 3. 停止导入
curl -X POST http://127.0.0.1:18799/api/migrate/stopbash

后处理：任务与技能生成Post-Processing: Task & Skill Generation

导入完成后，可选择对导入的记忆进行后处理：After import, optionally post-process imported memories:

• 任务生成：自动检测会话中的任务边界，为每个会话生成结构化摘要（目标/步骤/结果）。Task generation: Auto-detect task boundaries per session, generate structured summaries (goal/steps/result).
• 技能进化：从已完成的任务中提炼可复用技能，生成 SKILL.md 文件并安装到工作区。Skill evolution: Distill reusable skills from completed tasks, generate SKILL.md and install to workspace.

后处理为串行执行，逐条处理导入的会话。已处理过的会话自动跳过。支持选择只生成任务、只生成技能或两者同时执行。Post-processing runs serially, processing imported sessions one by one. Already processed sessions are auto-skipped. Choose task-only, skill-only, or both.

断点续传Resume & Stop

导入和后处理均支持随时暂停：Both import and post-processing support pause/resume:

• 点击 停止 按钮后，进度自动保存。Click Stop, progress auto-saved.
• 刷新页面后自动检测未完成的导入，恢复进度条显示。On page refresh, auto-detect incomplete imports and restore progress display.
• 再次点击开始即从上次中断处继续，已处理的记忆自动跳过。Click start again to continue from where you left off — processed memories are auto-skipped.
• 导入和后处理在后台运行，关闭 Viewer 页面不影响执行。Import and post-processing run in the background — closing the Viewer page won't interrupt them.

模块Modules

Capture

过滤 system/self-tool，剥离 OpenClaw 元数据。保留 user/assistant/tool。Filter system/self-tool, strip metadata. Keep user/assistant/tool.

Ingest

异步队列：语义分片 → LLM 摘要 → 向量化 → 智能去重（Top-5 相似 + LLM 判 DUPLICATE/UPDATE/NEW，UPDATE 合并摘要并追加内容）→ 存储；演化块记录 merge_history。Async queue: chunk → summary → embed → smart dedup (Top-5 similar + LLM DUPLICATE/UPDATE/NEW; UPDATE merges summary and appends content) → store; evolved chunks track merge_history.

任务总结Task Summarization

异步检测任务边界（LLM 话题 + 2h 超时）→ 结构化摘要（目标/步骤/结果）。Async boundary detection (LLM topic + 2h timeout) → structured summary (goal/steps/result).

技能进化Skill Evolution

规则过滤 → LLM 评估 → SKILL.md 生成（步骤/警告/脚本）/ 升级 → 质量评分 → 安装。Rule filter → LLM evaluate → SKILL.md (steps/warnings/scripts) / upgrade → score → install.

Recall

FTS5+Vector → RRF(k=60) → MMR(λ=0.7) → Decay(14d) → Normalize → Filter(≥0.45) → Top-K。自动关联 Task/Skill。FTS5+Vector → RRF(k=60) → MMR(λ=0.7) → Decay(14d) → Normalize → Filter(≥0.45) → Top-K. Auto-links Task/Skill.

Viewer

7 页：记忆 CRUD/搜索/演化标识、任务（对话气泡）、技能（版本/下载）、分析、日志（工具调用输入输出）、OpenClaw 原生记忆导入、在线配置。密码保护。7 pages: memory CRUD/search/evolution badges, tasks (chat bubbles), skills (versions/download), analytics, logs (tool call I/O), OpenClaw native memory import, online config. Password-protected.

检索算法Retrieval

RRF

MMR

时间衰减Recency

API

memory_search

query (required), maxResults (20), minScore (0.45), role. Returns excerpts（原文片段）+ chunkId / task_id，无 summary；经 LLM 相关性过滤。excerpts + chunkId/task_id, no summary; LLM relevance filter.

memory_get

获取记忆块完整原文。Get full original text of a memory chunk. chunkId, maxChars (optional).

memory_timeline

以 chunkId 为锚点的上下文邻居。Context neighbors by chunkId. chunkId, window (2).

task_summary

任务结构化摘要。Structured task summary. taskId or query.

skill_get / skill_install

skill_get 支持 skillId 或 taskId（按任务解析技能）；skill_install 安装到工作区。skill_get accepts skillId or taskId; skill_install installs to workspace.

memory_write_public

写入公共记忆（owner="public"），所有 Agent 均可检索。Write public memory (owner="public"), discoverable by all agents. content (required), summary (optional).

skill_search

搜索技能：FTS5 关键词 + 向量语义双通道，RRF 融合后经 LLM 判断相关性。Search skills via FTS5 + vector, RRF fusion, then LLM relevance judgment. query (required), scope ("mix" | "self" | "public", default "mix").

skill_publish / skill_unpublish

skill_publish 将技能设为公开，其他 Agent 可通过 skill_search 发现并安装。skill_unpublish 设为私有。skill_publish makes a skill public and discoverable via skill_search. skill_unpublish sets it private. skillId (required).

memory_viewer

返回 Viewer URL。Returns Viewer URL.

Viewer HTTP

GET /; POST /api/auth/*; GET /api/memories, /api/tasks, /api/skills, /api/stats, /api/logs, /api/log-tools, /api/config; POST/PUT/DELETE /api/memory/:id; PUT /api/skill/:id/visibility.

多智能体协同Multi-Agent Collaboration

MemOS 原生支持多 Agent 场景。每个 Agent 的记忆和任务通过 owner 字段隔离（格式 agent:{agentId}），检索时自动过滤为当前 Agent + public。MemOS natively supports multi-agent scenarios. Each agent's memories and tasks are isolated via an owner field (agent:{agentId}); retrieval automatically filters to current agent + public.

• 记忆隔离：Agent A 无法检索 Agent B 的私有记忆Memory Isolation: Agent A cannot retrieve Agent B's private memories
• 公共记忆：通过 memory_write_public 写入 owner="public" 的记忆，所有 Agent 可检索Public Memory: Use memory_write_public to write owner="public" memories discoverable by all agents
• 技能共享：通过 skill_publish 将技能设为公开，其他 Agent 可通过 skill_search 发现并安装Skill Sharing: Use skill_publish to make skills public; other agents discover and install via skill_search
• 技能检索：skill_search 支持 scope 参数（mix/self/public），FTS + 向量双通道 + RRF 融合 + LLM 相关性判断Skill Discovery: skill_search supports scope (mix/self/public), FTS + vector dual channel + RRF fusion + LLM relevance judgment

数据库Database

~/.openclaw/memos-local/memos.db, WAL. Tables: chunks (owner), chunks_fts, embeddings, tasks (owner), skills (owner, visibility), skill_versions, task_skills, skill_embeddings, skills_fts.

安全Security

Viewer 仅 127.0.0.1；密码 SHA-256；HttpOnly+SameSite Cookie；会话 24h；数据仅本地。127.0.0.1 only; SHA-256 password; HttpOnly+SameSite; 24h session; data stays local.

默认值Defaults

maxResults 6, maxResultsMax 20, minScore 0.45, rrfK 60, mmrLambda 0.7, recencyHalfLife 14d, vectorSearchMaxChunks 0 (search all), dedup 0.93, viewerPort 18799, taskIdle 2h, skillMinChunks 6.