install
source · Clone the upstream repo
git clone https://github.com/bigcola2020/openclaw-jarvis-memory
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/bigcola2020/openclaw-jarvis-memory "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/mem-redis" ~/.claude/skills/bigcola2020-openclaw-jarvis-memory-mem-redis && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/bigcola2020/openclaw-jarvis-memory "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/mem-redis" ~/.openclaw/skills/bigcola2020-openclaw-jarvis-memory-mem-redis && rm -rf "$T"
manifest:
skills/mem-redis/SKILL.mdsource content
Memory Buffer Skill
Redis-based short-term memory buffer for OpenClaw.
What It Does
Accumulates conversation turns in real-time and flushes to Qdrant daily.
Commands
# Manual save (all turns) python3 scripts/save_mem.py --user-id yourname # Retrieve from buffer python3 scripts/mem_retrieve.py --limit 10 # Search Redis + Qdrant python3 scripts/search_mem.py "your query"
Heartbeat Integration
Add to HEARTBEAT.md:
python3 /path/to/skills/mem-redis/scripts/hb_append.py
Cron
# Daily flush at 3:00 AM 0 3 * * * python3 scripts/cron_backup.py
Files
- Heartbeat: append new turns onlyhb_append.py
- Manual: save all turnssave_mem.py
- Daily: flush to Qdrantcron_backup.py
- Read from Redismem_retrieve.py
- Search Redis + Qdrantsearch_mem.py