灵枢 AutoBrain
灵枢 AutoBrain — OpenClaw 长期运行 AI 中枢运行时引擎套件。一键部署 40+ 引擎：五层记忆、自主任务循环、防幻觉、自进化、双模式分类、质量看板、身份漂移守卫、会话交接、故障转移、兼容层等。让 AI 不只是问答工具，而是真正长期陪伴你的个人核心。
灵枢 AutoBrain — OpenClaw 长期运行 AI 中枢运行时引擎套件。一键部署 40+ 引擎：五层记忆、自主任务循环、防幻觉、自进化、双模式分类、质量看板、身份漂移守卫、会话交接、故障转移、兼容层等。让 AI 不只是问答工具，而是真正长期陪伴你的个人核心。
#auto-brain#auto-install#engine#latest#memory#orchestrator#plugin-sdk#runtime#self-evolution
概述
🦞 灵枢AutoBrain — Skill Page
Long-term memory, anti-hallucination, self-evolution, and workflow orchestration for OpenClaw. 90+ Python engines across 8 engine groups + 3 subsystems.
Quick Install
openclaw plugins install --dangerously-force-unsafe-install ./crusheart-pack/
# Then restart gateway
Features
| Feature | Description |
|---|---|
| --------- | ------------- |
| 🧠 Long-term Memory | 5-layer memory + DAG context management + memory consolidation engine |
| 🛡️ Anti-Hallucination | Authority whitelist + multi-source cross-verification (16 engines) |
| 🔄 Self-Evolution | LLM-as-Judge self-scoring + Reflexion reflection (pattern, root cause, fix) |
| 🎯 Dual-Mode + R-CCAM | Fast path for simple Q&A, deep reasoning for complex tasks |
| 🔍 Enhanced Retrieval | Query rewriting + RRF fusion + retrieval confidence evaluation |
| 🩺 Daily Maintenance | 01:00 unified cron: health check + cleanup + memory + dream + replay + memory scan |
| 🔀 Workflow Engine | Multi-skill coordination, conflict detection, task routing, rule engine |
| 📋 Context Capsule | DAG-based session handoff with SQLite-backed context graph |
| 📁 Auto-Scan | First-install: memory scan + skill classification + correction init |
| 🔄 Version Check | One-time check against clawhub.ai on install, daily re-check at 05:00 |
Architecture
plugin (index.js) ──► 90+ Python engines ──► 10-stage message pipeline
8 engine groups: init/memory/quality/operations/workflow/hooks/tools/compat
+ 3 subsystems: pipeline/planner/capability
+ 8 auto-deployed scripts
Plugin slot: exclusive — detects any overlapping plugin and blocks install
Cron: unified maintenance (01:00), engine init + version check (05:00)
Resources
- Architecture Reference:
bundle/ARCHITECTURE.md— full file lookup guide - Readme (English):
README.md - Readme (Chinese):
readme_cn.md - Skill (Chinese):
skill_cn.md - Install Guide:
bundle/INSTALL_GUIDE.md
Feedback: HIM603070@gmail.com
版本历史
共 3 个版本
-
v6.3.1 当前2026-05-29 13:18 安全 安全
-
v5.2.202026-05-20 04:56 安全 安全
-
v5.2.02026-05-19 10:58 安全 安全
🔗 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。
★ 1,423
📥 326,405
ai-agent
Skill Vetter
spclaudehome
AI智能体技能安全预审工具。安装ClawdHub、GitHub等来源技能前，检查风险信号、权限范围及可疑模式。
★ 1,245
📥 272,154