Agent Memory Pro
- **name**: Agent Memory Pro
by bytesagain · published 2026-03-22
$ claw add gh:bytesagain/bytesagain-agent-memory-probe-1773358981-1# Agent Memory Pro
FAQ
**Q: How is this different from basic agent memory?**
A: Structured categories, MD5 deduplication, and full export — not flat file storage.
**Q: Where are memories stored?**
A: `~/agent-memory/` with typed subdirs: learnings, facts, decisions, archive, exports.
**Q: Can I migrate memories between agents?**
A: Yes — `export` creates portable Markdown any agent can ingest.
**Q: How does consolidation work?**
A: MD5 hashing detects exact duplicates and reports them for cleanup.
Commands
| Command | Purpose |
|---------|---------|
| `init` | Setup structured memory dirs |
| `save` | Store categorized learning |
| `recall` | Keyword search with ranking |
| `review` | Show recent 72h memories |
| `consolidate` | Hash-based deduplication |
| `export` | Portable Markdown export |
| `stats` | Per-category statistics |
| `forget` | Selective pruning |
More tools from the same signal band
Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).
Sign plugins, rotate agent credentials without losing identity, and publicly attest to plugin behavior with verifiable claims and authenticated transfers.
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your...