Per-Agent Memory Compression Skill
by bensk2001
安装
claude skill add --url github.com/openclaw/skills/tree/main/skills/bensk2001/per-agent-compression-universal文档
Overview
This skill automates weekly memory consolidation for multi-agent OpenClaw deployments. It discovers all agents with workspaces and registers staggered cron tasks that compress old daily notes into long-term memory files.
Key Features
- Auto-discovery: Finds all agents via
openclaw agents list - Workspace isolation: Each agent compresses its own memory
- State persistence: Tracks processed notes in
.compression_state.json - Deduplication: Avoids duplicate entries
- Domain awareness: Includes DOMAIN_CONTEXT for tailored extraction
- Zero config: Just run
./install.sh
Installation
cd /root/.openclaw/workspace/skills/per-agent-compression-universal
./install.sh
This creates 5 staggered tasks (if you have 5 agents) running Sundays 03:00-05:00 Shanghai time.
What It Does
- Pre-check paths and initialize state
- List daily notes older than 7 days (skip recent)
- Sort oldest first, process up to 5 notes per run
- For each note:
- Read content
- Extract factual info (preferences, decisions, personal info)
- Append to target files with date headers
- Move original to
memory/processed/
- Update state file
- Clean working buffer
- Send DingTalk summary
File Structure
Each agent workspace should have:
memory/YYYY-MM-DD.md(daily notes)USER.md,IDENTITY.md,SOUL.md,MEMORY.md(targets)
After running:
memory/.compression_state.json(state tracking)memory/processed/(moved old notes)
Customization
Edit install.sh to adjust:
- Stagger offsets (
OFFSETSarray) - Domain context per agent (
DOMAIN_CONTEXTassociative array) - Cron expression (currently Sundays)
Troubleshooting
- Task hangs: Check STATE_FILE path uses
{WORKSPACE}(uppercase), not{workspace} - No notes processed: Ensure there are daily notes older than 7 days
- Timeout: Increase
--timeoutin install.sh (default 1200s) - Delivery fails: Verify DingTalk connector configured with
tofield
Uninstall
./uninstall.sh
Removes all per_agent_compression_* tasks.
Version
Current: 1.3.4 (fixes STATE_FILE case sensitivity bug)
Support
See README.md for full documentation.
相关 Skills
Claude接口
by anthropics
面向接入 Claude API、Anthropic SDK 或 Agent SDK 的开发场景,自动识别项目语言并给出对应示例与默认配置,快速搭建 LLM 应用。
✎ 想把Claude能力接进应用或智能体,用claude-api上手快、兼容Anthropic与Agent SDK,集成路径清晰又省心
提示工程专家
by alirezarezvani
覆盖Prompt优化、Few-shot设计、结构化输出、RAG评测与Agent工作流编排,适合分析token成本、评估LLM输出质量,并搭建可落地的AI智能体系统。
✎ 把提示优化、LLM评测到RAG与智能体设计串成一套方法,适合想系统提升AI开发效率的人。
智能体流程设计
by alirezarezvani
面向生产级多 Agent 编排,梳理顺序、并行、分层、事件驱动、共识五种工作流设计,覆盖 handoff、状态管理、容错重试、上下文预算与成本优化,适合搭建复杂 AI 协作系统。
✎ 帮你把多智能体流程设计、编排和自动化统一起来,复杂工作流也能更稳地落地,适合追求强控制力的团队。
相关 MCP 服务
顺序思维
编辑精选by Anthropic
Sequential Thinking 是让 AI 通过动态思维链解决复杂问题的参考服务器。
✎ 这个服务器展示了如何让 Claude 像人类一样逐步推理,适合开发者学习 MCP 的思维链实现。但注意它只是个参考示例,别指望直接用在生产环境里。
知识图谱记忆
编辑精选by Anthropic
Memory 是一个基于本地知识图谱的持久化记忆系统,让 AI 记住长期上下文。
✎ 帮 AI 和智能体补上“记不住”的短板,用本地知识图谱沉淀长期上下文,连续对话更聪明,数据也更可控。
PraisonAI
编辑精选by mervinpraison
PraisonAI 是一个支持自反思和多 LLM 的低代码 AI 智能体框架。
✎ 如果你需要快速搭建一个能 24/7 运行的 AI 智能体团队来处理复杂任务(比如自动研究或代码生成),PraisonAI 的低代码设计和多平台集成(如 Telegram)让它上手极快。但作为非官方项目,它的生态成熟度可能不如 LangChain 等主流框架,适合愿意尝鲜的开发者。