- SyncSettingsRepository + DatasetPermissionRepository with RBAC - Script deploy/run/undeploy API with import sandboxing - User sync settings API with permission checks - 4 CLI skills (connectors, security, notifications, corporate-memory) - Kamal production + staging configs - GitHub Actions CI + deploy workflows - 91 total tests passing
1.1 KiB
1.1 KiB
Corporate Memory — Knowledge sharing and governance
What It Is
Corporate memory collects knowledge from all analysts' CLAUDE.local.md files and makes it available to everyone through a curated catalog.
How It Works
- Analysts write insights in their CLAUDE.local.md
da sync --upload-onlypushes content to server- Server processes with LLM (Haiku) to extract knowledge items
- Items go through governance (pending → approved/mandatory)
- Approved items are distributed as Claude rules
Governance Flow
- pending: New item, awaiting review
- approved: Available to all users
- mandatory: Force-pushed to all users' rules
- rejected: Not distributed
Admin Commands
# View pending items (via web UI or API)
da query "SELECT id, title, status FROM system.knowledge_items WHERE status='pending'" --remote
# Approve/reject via API
curl -X PUT http://server:8000/api/memory/<id>/status?new_status=approved -H "Authorization: Bearer $TOKEN"
Voting
Users can upvote/downvote knowledge items to surface the most useful ones.