Multi-layer memory system for LLM agents. Fresh daily layer, mesh graph indexing, auto-logging, cross-layer search, and full compliance checks.
Built for OpenClaw. Works with any agent that can run Python.
| Layer | File | Purpose |
|---|---|---|
| ------- | ------ | --------- |
| Fresh | memory/fresh/today.md | Daily notes, 5-day rotation |
| Mesh | memory/mesh.json | Graph nodes + search index |
| Log | scripts/auto_log | Auto-log every interaction |
| Search | scripts/memory_search | Cross-layer search (fresh → daily → mesh → raw → long-term) |
| Check | scripts/memory_check | 10-point compliance check (memcheck) |
mem-bridge init # Rotate fresh layer, create today.md
auto_log "msg" "reply" # Log an interaction
memory_search "query" # Search all memory layers
memcheck # Full 10-point compliance check
| Tool | Source |
|---|---|
| ------ | -------- |
mem-bridge | memory/bridge.py — fresh-layer rotation + checkpoint management |
auto_log | scripts/auto_log.py — interaction logger |
memory_search | scripts/memory_search.py — multi-layer search across all memory stores |
memcheck | scripts/memory_check.py — 10-point compliance check runner |
Put bridge.py in memory/ and scripts in scripts/ of your agent workspace. Symlink or add to PATH:
ln -s $(pwd)/scripts/* ~/.local/bin/
ln -s $(pwd)/memory/bridge.py ~/.local/bin/mem-bridge
On session start, run:
mem-bridge init
https://github.com/mozz0/MeshMorize
_Made by mozz0 · Released under MIT_
共 1 个版本