# Hivemind Memory

Global team and org memory powered by Activeloop.

- Repository: https://github.com/activeloopai/hivemind (1640 stars)
- Category: Engineering
- License: Apache-2.0
- Last updated: 2026-10-24
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add activeloopai/hivemind --skill hivemind-memory -g -a claude-code -y`
Codex: `npx skills add activeloopai/hivemind --skill hivemind-memory -g -a codex -y`
Cursor: `npx skills add activeloopai/hivemind --skill hivemind-memory -g -a cursor -y`
Gemini CLI: `npx skills add activeloopai/hivemind --skill hivemind-memory -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add activeloopai/hivemind`

## Description

Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Hivemind Memory

You have TWO memory sources. ALWAYS check BOTH when the user asks you to recall, remember, or look up ANY information:

1. **Your built-in memory** (`~/.claude/`), personal per-project notes
2. **Hivemind global memory** (`~/.deeplake/memory/`), global memory shared across all sessions, users, and agents in the org

## Memory Structure

```
~/.deeplake/memory/
├── index.md                          ← START HERE, table of all sessions
├── summaries/
│   ├── session-abc.md                ← AI-generated wiki summary
│   └── session-xyz.md
└── sessions/
    └── username/
        ├── user_org_ws_slug1.jsonl   ← raw session data
        └── user_org_ws_slug2.jsonl
```

## How to Search

1. **First**: Read `~/.deeplake/memory/index.md`, quick scan of all sessions with dates, projects, descriptions
2. **If you need details**: Read the specific summary at `~/.deeplake/memory/summaries/<session>.md`
3. **If you need raw data**: Read the session JSONL at `~/.deeplake/memory/sessions/<user>/<file>.jsonl`
4. **Keyword search**: `Grep pattern="keyword" path="~/.deeplake/memory"`

Do NOT jump straight to reading raw JSONL files. Always start with index.md and summaries.

## Organization Management

The 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 Each argument is separate, do NOT quote subcommands together:
- `node "<AUTH_CMD>" login`, SSO login
- `node "<AUTH_CMD>" whoami`, show current user/org
- `node "<AUTH_CMD>" org list`, list organizations
- `node "<AUTH_CMD>" org switch <name-or-id>`, switch organization
- `node "<AUTH_CMD>" workspaces`, list workspaces
- `node "<AUTH_CMD>" workspace <id>`, switch workspace
- `node "<AUTH_CMD>" invite <email> <ADMIN|WRITE|READ>`, invite member (ALWAYS ask user which role first)
- `node "<AUTH_CMD>" members`, list members
- `node "<AUTH_CMD>" remove <user-id>`, remove member
- `node "<AUTH_CMD>" --help`, show all commands

## Skill Management (skillify)

The rest: https://github.com/activeloopai/hivemind/blob/HEAD/harnesses/claude-code/skills/hivemind-memory/SKILL.md