{"id":"hivemind-memory","name":"hivemind-memory","summary":"グローバルチームおよび組織のメモリはActiveloopで提供されています。情報を思い出す際は、必ず内蔵メモリとハイブマインドメモリの両方を確認してください。","body":"# Hivemind Memory\n\nYou have TWO memory sources. ALWAYS check BOTH when the user asks you to recall, remember, or look up ANY information:\n\n1. **Your built-in memory** (`~/.claude/`) — personal per-project notes\n2. **Hivemind global memory** (`~/.deeplake/memory/`) — global memory shared across all sessions, users, and agents in the org\n\n## Memory Structure\n\n```\n~/.deeplake/memory/\n├── index.md                          ← START HERE — table of all sessions\n├── summaries/\n│   ├── session-abc.md                ← AI-generated wiki summary\n│   └── session-xyz.md\n└── sessions/\n    └── username/\n        ├── user_org_ws_slug1.jsonl   ← raw session data\n        └── user_org_ws_slug2.jsonl\n```\n\n## How to Search\n\n1. **First**: Read `~/.deeplake/memory/index.md` — quick scan of all sessions with dates, projects, descriptions\n2. **If you need details**: Read the specific summary at `~/.deeplake/memory/summaries/<session>.md`\n3. **If you need raw data**: Read the session JSONL at `~/.deeplake/memory/sessions/<user>/<file>.jsonl`\n4. **Keyword search**: `Grep pattern=\"keyword\" path=\"~/.deeplake/memory\"`\n\nDo NOT jump straight to reading raw JSONL files. Always start with index.md and summaries.\n\n## Organization Management\n\nThe 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 Each argument is separate — do NOT quote subcommands together:\n- `node \"<AUTH_CMD>\" login` — SSO login\n- `node \"<AUTH_CMD>\" whoami` — show current user/org\n- `node \"<AUTH_CMD>\" org list` — list organizations\n- `node \"<AUTH_CMD>\" org switch <name-or-id>` — switch organization\n- `node \"<AUTH_CMD>\" workspaces` — list workspaces\n- `node \"<AUTH_CMD>\" workspace <id>` — switch workspace\n- `node \"<AUTH_CMD>\" invite <email> <ADMIN|WRITE|READ>` — invite member (ALWAYS ask user which role first)\n- `node \"<AUTH_CMD>\" members` — list members\n- `node \"<AUTH_CMD>\" remove <user-id>` — remove member\n- `node \"<AUTH_CMD>\" --help` — show all commands\n\n## Skill Management (skillify)\n\nHivemind can mine reusable skills from agent session logs and share them across your team. Each argument is separate — do NOT quote subcommands together.\n\n- `hivemind skillify` — show current scope, team, install location, per-project state\n- `hivemind skillify pull` — sync project skills from the org table to local FS\n- `hivemind skillify pull --user <email>` — only skills authored by that user\n- `hivemind skillify pull --users <a,b,c>` — multiple authors (CSV)\n- `hivemind skillify pull --all-users` — explicit \"no author filter\" (default)\n- `hivemind skillify pull --to <project|global>` — install location (project=cwd/.claude/skills, global=~/.claude/skills)\n- `hivemind skillify pull --dry-run` — preview without touching disk\n- `hivemind skillify pull --force` — overwrite local files even if up-to-date (creates .bak)\n- `hivemind skillify pull <skill-name>` — pull only that one skill (combines with --user)\n- `hivemind skillify push <skill-name>` — upload a local skill to the org table (inverse of pull; re-push lands a new version)\n- `hivemind skillify push --from <project|global>` — which local skills dir to read (default: project)\n- `hivemind skillify push --dry-run` — preview without writing to the org table\n- `hivemind skillify unpull` — remove every skill previously installed by pull\n- `hivemind skillify unpull --user <email>` — remove only that author's pulls\n- `hivemind skillify unpull --not-mine` — remove all pulls except your own\n- `hivemind skillify unpull --dry-run` — preview without touching disk\n- `hivemind skillify scope <me|team>` — sharing scope for newly mined skills\n- `hivemind skillify install <project|global>` — default install location for new skills\n- `hivemind skillify promote <skill-name>` — move a project skill to the global location\n- `hivemind skillify team add|remove|list <username>` — manage team member list\n- `hivemind skillify mine-local` — one-shot: mine skills from local sessions, no auth needed\n\n## Embeddings (semantic memory search)\n\nOpt-in, persisted in `~/.deeplake/config.json`.\n\n- `hivemind embeddings install` — download deps (~600MB), symlink agents, set enabled:true\n- `hivemind embeddings enable` — flip enabled:true (run install first if deps missing)\n- `hivemind embeddings disable` — flip enabled:false + SIGTERM daemon (deps stay on disk)\n- `hivemind embeddings uninstall [--prune]` — remove agent symlinks + disable; --prune wipes deps too\n- `hivemind embeddings status` — show config + deps + per-agent link state\n\n## Important: Bash Only\n\nOnly use bash commands (cat, ls, grep, echo, jq, head, tail, sed, awk, etc.) to interact with `~/.deeplake/memory/`. Do NOT use python, python3, node, curl, or other interpreters — they are not available in the memory filesystem. If a task seems to require Python, rewrite it using bash tools (e.g., `cat file.json | jq 'keys | length'`).\n\n## Limits\n\nIf a file returns empty after 2 attempts, skip it and move on. Report what you found rather than exhaustively retrying.\n\n## Getting Started\n\nAfter installing the plugin:\n1. Run `/hivemind:login` to authenticate\n2. Start using memory — ask questions, Claude automatically captures and searches\n\n## Configuration\n\n- `HIVEMIND_DEBUG=1 claude` — enable verbose logging to `~/.deeplake/hook-debug.log`\n- `HIVEMIND_CAPTURE=false claude` — disable session capture","author":"@activeloopai","ownerProfile":null,"authorContacts":null,"sourceUrl":"https://github.com/activeloopai/hivemind/tree/main/harnesses/claude-code/skills/hivemind-memory","license":"Apache-2.0","category":"document","lang":"en","tokens":1432,"stars":0,"calls30d":1,"claimed":false,"visibility":"public","origin":"crawler","version":"0.1.0","createdAt":"2026-08-22","updatedAt":"2026-08-22","files":[],"requires":{"mcp":[],"tools":["Grep Read Bash"]},"safety":{"flags":[],"scannedAt":"2026-08-22","hasScripts":false,"networkEndpoints":[]}}