hivemind

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** — personal per-project notes from the host agent
62. **Hivemind global memory** — global memory shared across all sessions, users, and agents in the org, accessed via the tools below
7 
8## Memory Structure
9 
10```
11/index.md                           ← START HERE — table of all sessions
12/summaries/
13  <username>/
14    <session-id>.md                 ← AI-generated wiki summary per session
15/sessions/
16  <username>/
17    <user_org_ws_slug>.jsonl        ← raw session data
18```
19 
20## How to Search
21 
221. **First**: call `hivemind_index()` — table of all sessions with dates, projects, descriptions
232. **If you need details**: call `hivemind_read("/summaries/<username>/<session>.md")`
243. **If you need raw data**: call `hivemind_read("/sessions/<username>/<file>.jsonl")`
254. **Keyword search**: call `hivemind_search("keyword")` — substring search across both summaries and sessions, returns `path:line` hits
26 
27Do NOT jump straight to reading raw JSONL files. Always start with `hivemind_index` and summaries.
28 
29## Organization Management
30 
31- `/hivemind_login` — sign in via device flow
32- `/hivemind_capture` — toggle capture on/off (off = no data sent)
33- `/hivemind_whoami` — show current org and workspace
34- `/hivemind_orgs` — list organizations
35- `/hivemind_switch_org <name-or-id>` — switch organization
36- `/hivemind_workspaces` — list workspaces
37…