How do I install the Memory Consolidate skill?

Run npx skillmds@latest add dvcrn/memory-consolidate-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Memory Consolidate safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: executes scripts, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Memory Consolidate?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Memory Consolidate free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Memory Consolidate?

dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Memory Consolidate by dvcrn — Agent Skill

Name: Memory Consolidate
Rating: 4.666666666666667 (3 reviews)
Author: dvcrn

Memory Consolidate

Persistent memory system for OpenClaw agents: reads session logs, extracts facts/decisions/solutions, manages temperature-based lifecycle, and generates MEMORY_SNAPSHOT.md injected into every session. ALWAYS use this skill when the user mentions: memory consolidation, 记忆整理, agent memory, MEMORY_SNAPSHOT, memory health, SNR, signal noise ratio, semantic pipeline, memory cron, session log extraction, facts not being saved, memory stale or missing, 内存优化, optimize agent memory, install memory, memory not working, memory consolidate 报错, cron 怎么配 (when related to memory), 每天自动整理记忆, or any question about why the agent forgets things between sessions. Also activate when user says memory is stale, missing, or broken.

dvcrn Updated Sep 22, 2026 32 repo stars

File contents

memory-consolidate

Scripts live in the directory containing this SKILL.md. No copying needed. OPENCLAW_WORKSPACE (default: ~/.openclaw/workspace) tells scripts where to read/write.

Install

Create required directories:

mkdir -p $OPENCLAW_WORKSPACE/memory/structured/{archive,candidates,semantic}

Patch OpenClaw config to inject snapshot into agent sessions:

gateway config.patch path="hooks.internal" raw='{"enabled":true,"entries":{"bootstrap-extra-files":{"enabled":true,"paths":["MEMORY_SNAPSHOT.md"]}}}'

Add daily cron (read timezone from USER.md, default UTC):

cron add job={
  "name": "Memory Consolidation (daily)",
  "schedule": {"kind": "cron", "expr": "0 3 * * *", "tz": "<tz_from_USER.md>"},
  "payload": {
    "kind": "agentTurn",
    "message": "bash $OPENCLAW_WORKSPACE/scripts/memory_consolidate_report.sh",
    "thinking": "off",
    "timeoutSeconds": 300
  },
  "sessionTarget": "isolated",
  "delivery": {"mode": "announce"}
}

Run initial consolidation and verify:

bash $OPENCLAW_WORKSPACE/scripts/memory_consolidate_report.sh

Semantic Pipeline (LLM-powered)

memory_consolidate_report.sh runs the full pipeline including a semantic consolidation step powered by claude-haiku-4-5-20251001 via the tui provider. This is auto-configured from openclaw.json — no manual API key setup needed. The LLM step clusters related memories, deduplicates, and improves signal quality in MEMORY_SNAPSHOT.md.

Identity

Auto-detected from IDENTITY.md (assistant name) and USER.md (owner name, timezone, language). No config needed if these files exist with - **Key:** Value format.

Config

Edit config.yaml in the directory containing this SKILL.md:

ingest.agent_ids — which agents to scan (default: "main", or ["main", "worker"])
ingest.session_hours — lookback window (default: 24)
tag_rules — project keyword → tag mapping
temperature.age_lambda — decay speed (default: 0.07)

Health check

python3 $OPENCLAW_WORKSPACE/scripts/memory_consolidate_observe.py

🟢 healthy / 🟡 watch / 🔴 needs tuning

Troubleshooting

Symptom	Fix
Snapshot shows "Assistant"/"User"	Ensure IDENTITY.md/USER.md have `Name:` format
LLM semantic step fails	Check `tui` provider config in `openclaw.json` has `baseUrl` and `apiKey`
Semantic pipeline degraded	Run `memory_candidate_extract.py`, check import errors
SNR too low	Increase `temperature.age_lambda` in config.yaml
No cold items after 2 weeks	Increase `age_lambda` (0.07 default should work)
Memory not updating	Verify `OPENCLAW_WORKSPACE` env var is set and cron job is active

---name: memory-consolidate-2description: Persistent memory system for OpenClaw agents: reads session logs, extracts facts/decisions/solutions, manages temperature-based lifecycle, and generates MEMORY_SNAPSHOT.md injected into every session. ALWAYS use this skill when the user mentions: memory consolidation, 记忆整理, agent memory, MEMORY_SNAPSHOT, memory health, SNR, signal noise ratio, semantic pipeline, memory cron, session log extraction, facts not being saved, memory stale or missing, 内存优化, optimize agent memory, install memory, memory not working, memory consolidate 报错, cron 怎么配 (when related to memory), 每天自动整理记忆, or any question about why the agent forgets things between sessions. Also activate when user says memory is stale, missing, or broken.---# memory-consolidateScripts live in the directory containing this SKILL.md. No copying needed.`OPENCLAW_WORKSPACE` (default: `~/.openclaw/workspace`) tells scripts where to read/write.## InstallCreate required directories:```bashmkdir -p $OPENCLAW_WORKSPACE/memory/structured/{archive,candidates,semantic}```Patch OpenClaw config to inject snapshot into agent sessions:```gateway config.patch path="hooks.internal" raw='{"enabled":true,"entries":{"bootstrap-extra-files":{"enabled":true,"paths":["MEMORY_SNAPSHOT.md"]}}}'```Add daily cron (read timezone from USER.md, default UTC):```cron add job={ "name": "Memory Consolidation (daily)", "schedule": {"kind": "cron", "expr": "0 3 * * *", "tz": "<tz_from_USER.md>"}, "payload": { "kind": "agentTurn", "message": "bash $OPENCLAW_WORKSPACE/scripts/memory_consolidate_report.sh", "thinking": "off", "timeoutSeconds": 300 }, "sessionTarget": "isolated", "delivery": {"mode": "announce"}}```Run initial consolidation and verify:```bashbash $OPENCLAW_WORKSPACE/scripts/memory_consolidate_report.sh```## Semantic Pipeline (LLM-powered)`memory_consolidate_report.sh` runs the full pipeline including a semantic consolidation step powered by `claude-haiku-4-5-20251001` via the `tui` provider. This is auto-configured from `openclaw.json` — no manual API key setup needed. The LLM step clusters related memories, deduplicates, and improves signal quality in MEMORY_SNAPSHOT.md.## IdentityAuto-detected from `IDENTITY.md` (assistant name) and `USER.md` (owner name, timezone, language). No config needed if these files exist with `- **Key:** Value` format.## ConfigEdit `config.yaml` in the directory containing this SKILL.md:- `ingest.agent_ids` — which agents to scan (default: `"main"`, or `["main", "worker"]`)- `ingest.session_hours` — lookback window (default: 24)- `tag_rules` — project keyword → tag mapping- `temperature.age_lambda` — decay speed (default: 0.07)## Health check```bashpython3 $OPENCLAW_WORKSPACE/scripts/memory_consolidate_observe.py```🟢 healthy / 🟡 watch / 🔴 needs tuning## Troubleshooting| Symptom | Fix ||---------|-----|| Snapshot shows "Assistant"/"User" | Ensure IDENTITY.md/USER.md have `**Name:**` format || LLM semantic step fails | Check `tui` provider config in `openclaw.json` has `baseUrl` and `apiKey` || Semantic pipeline degraded | Run `memory_candidate_extract.py`, check import errors || SNR too low | Increase `temperature.age_lambda` in config.yaml || No cold items after 2 weeks | Increase `age_lambda` (0.07 default should work) || Memory not updating | Verify `OPENCLAW_WORKSPACE` env var is set and cron job is active |

Frequently asked questions