Bring admin UI, audit-log messages, code comments, and analyst-facing skill docs in line with the post-bootstrap CLI surface (`agnes pull`, `agnes push`, `agnes init`, `agnes snapshot create`). The legacy `_LEGACY_STRINGS` detection tuple in `app/api/claude_md.py` and the hook upgrade markers in `cli/lib/hooks.py` are intentionally left as-is — they exist precisely to flag pre-rewrite content for re-authoring. Strip "(folded from `da metrics list`)" / "(lifted from `da metrics show`)" / "Replaces the old `da analyst status`" docstring noise — the rename history is in CHANGELOG.md, not in module docstrings.
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
agnes pushuploads sessions and CLAUDE.local.md to the 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)
agnes 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.