TREE(74): training modules, entity profiles, 2890 references, keyword indices SPROUT(42): knowledge pages, project docs, curated source material SEED(164): daily notes, raw session logs, unprocessed material Updated AUDIT_MANIFEST.json with growth classifications.
1.7 KiB
1.7 KiB
pageType, id, title, sourceType, sourcePath, ingestedAt, updatedAt, status, growth
| pageType | id | title | sourceType | sourcePath | ingestedAt | updatedAt | status | growth |
|---|---|---|---|---|---|---|---|---|
| source | source.2026-04-08 | 2026-04-08 | local-file | /home/topher/.openclaw/workspace-2890-bot/memory/2026-04-08.md | 2026-05-02T21:37:52.203Z | 2026-05-02T21:37:52.203Z | active | seed |
2026-04-08
Source
- Type:
local-file - Path:
/home/topher/.openclaw/workspace-2890-bot/memory/2026-04-08.md - Bytes: 1091
- Updated: 2026-05-02T21:37:52.203Z
Content
# 2026-04-08 - Infrastructure Setup
## Infrastructure Access (FRC Isolation)
- **Ollama embeddings**: http://100.91.1.57:11434 with nomic-embed-text model (semantic memory search)
- **Qdrant vector DB**: http://100.91.1.57:6333
- **FRC collection**: Create "2890-knowledge" — DO NOT use brewery collection
- **Server**: CasaOS at 100.91.1.57, SSH key same as CasaOS (~/.ssh/casaos_key as topher@media)
- **Dreaming**: Fires at 3 AM if heartbeat enabled (30m intervals in agent config)
- **Memory search**: Provider = ollama, model = nomic-embed-text, remote.baseUrl = http://100.91.1.57:11434
- **Data isolation**: FRC workspace files and Qdrant collection separate from brewery data
## Rule
- Infrastructure details are for bot use only — not to be shared with team
- FRC data stays isolated from brewery data
- Use shared infrastructure (Ollama, Qdrant) read-only, no mixing
## Session Notes
- Topher provided infrastructure details for new OpenClaw capabilities
- No info to be shared with team about this setup
- Bot now has access to semantic memory search and dreaming features
Notes
Related
- No related pages yet.