← 返回
未分类 Key 中文

Human-Like Memory Plugin

Long-term memory plugin for OpenClaw: automatic recall, storage, and agent tools
OpenClaw长期记忆插件:自动回忆、存储与智能体工具
humanlike2026 humanlike2026 来源
未分类 clawhub v1.0.1 1 版本 100000 Key: 需要
★ 0
Stars
📥 438
下载
💾 0
安装
1
版本
#latest

概述

Human-Like Memory Plugin

Long-term memory plugin for OpenClaw. Gives your agent the ability to remember past conversations, user preferences, and important context across sessions.

Features

  • Automatic memory recall before each response
  • Automatic conversation storage after each response
  • Agent-callable tools: memory_search and memory_store
  • Registered as a first-class memory slot (kind: "memory")
  • Runtime reads OpenClaw plugin config only
  • Privacy-preserving by default: platform metadata extraction is disabled unless explicitly enabled
  • Requires OpenClaw >= 2026.2.0

Setup

1. Get API Key

Visit plugin.human-like.me → Register → Copy your mp_xxx key

2. Install

openclaw plugins install @humanlikememory/human-like-mem

3. Configure

# Set API key (required)

openclaw config set plugins.entries.human-like-mem.config.apiKey "mp_your_key_here"

# Set as the active memory engine

openclaw config set plugins.slots.memory human-like-mem

# Enable memory search for the agent

openclaw config set agents.defaults.memorySearch '{"enabled":true}' --strict-json

4. Restart

openclaw restart

5. Verify

openclaw status

You should see:

Memory │ 0 files · 0 chunks · sources remote-api · plugin human-like-mem · vector ready

Configuration Options

All options via openclaw config set plugins.entries.human-like-mem.config. :

KeyTypeDefaultDescription
---------------------------------
apiKeystring(required)Your API key from plugin.human-like.me
baseUrlstringhttps://plugin.human-like.meAPI endpoint
userIdstringopenclaw-userUser identifier
agentIdstringauto-detectedAgent identifier
recallEnabledbooleantrueEnable automatic memory recall
addEnabledbooleantrueEnable automatic memory storage
memoryLimitNumbernumber6Max memories to recall per turn
minScorenumber0.1Minimum relevance score (0-1)
minTurnsToStorenumber5Store after N conversation turns
stripPlatformMetadatabooleantrueDo not send Feishu/Discord platform IDs unless explicitly enabled

Agent Tools

Once installed, your agent can actively use memory:

  • memory_search — Search past conversations and stored knowledge
  • memory_store — Save important information for future recall

Troubleshooting

ProblemSolution
-------------------
"API key not configured"openclaw config set plugins.entries.human-like-mem.config.apiKey "mp_xxx"
"unavailable" in statusSet plugins.slots.memory to human-like-mem
Check logs`openclaw logs \grep "Memory Plugin"`

License

Apache-2.0

版本历史

共 1 个版本

  • v1.0.1 当前
    2026-05-03 08:18 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-agent

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,427 📥 326,917
it-ops-security

Publish npm + ClawHub

humanlike2026
将 OpenClaw 技能或插件发布至 npm 与 ClawHub,使用受保护的工作流,适用于用户请求发布、上线或重新发布的场景。
★ 0 📥 469
ai-agent

self-improving agent

pskoett
记录自身发现以实现自我改进的技能
★ 4,142 📥 916,925