hivemind-memory

1# Hivemind Memory
2 
3You have TWO memory sources. ALWAYS check BOTH when the user asks you to recall, remember, or look up ANY information:
4 
51. **Your built-in memory** (`~/.claude/`) — personal per-project notes
62. **Hivemind global memory** (`~/.deeplake/memory/`) — global memory shared across all sessions, users, and agents in the org
7 
8## Memory Structure
9 
10```
11~/.deeplake/memory/
12├── index.md                          ← START HERE — table of all sessions
13├── summaries/
14│   ├── session-abc.md                ← AI-generated wiki summary
15│   └── session-xyz.md
16└── sessions/
17    └── username/
18        ├── user_org_ws_slug1.jsonl   ← raw session data
19        └── user_org_ws_slug2.jsonl
20```
21 
22## How to Search
23 
241. **First**: Read `~/.deeplake/memory/index.md` — quick scan of all sessions with dates, projects, descriptions
252. **If you need details**: Read the specific summary at `~/.deeplake/memory/summaries/<session>.md`
263. **If you need raw data**: Read the session JSONL at `~/.deeplake/memory/sessions/<user>/<file>.jsonl`
274. **Keyword search**: `Grep pattern="keyword" path="~/.deeplake/memory"`
28 
29Do NOT jump straight to reading raw JSONL files. Always start with index.md and summaries.
30 
31## Organization Management
32 
33The auth command path is injected at session start. Use the exact path from the session context. Each argument is separate — do NOT quote subcommands together:
34- `node "<AUTH_CMD>" login` — SSO login
35- `node "<AUTH_CMD>" whoami` — show current user/org
36…