Hivemind Memory

This turns Claude into a team memory system backed by Activeloop's Deep Lake. Every conversation gets indexed into a shared knowledge base at ~/.deeplake/memory/ with summaries, raw session logs, and a master index. When you ask Claude to recall something, it checks both its built-in project memory and the global Hivemind store. The skillify subcommand is particularly clever: it mines reusable skills from your team's session logs and lets you pull them into your own projects by author or scope. There's optional semantic search via embeddings if you need it. Works entirely through bash tools, so no Python or Node dependencies in the memory layer. Good for teams who want institutional memory without switching tools.

GitHub stars: 1.1K
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add activeloopai/hivemind --skill hivemind-memory --agent claude-code

Installs into .claude/skills of the current project.

Files

Hivemind Memory

You have persistent memory at ~/.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

First: Read ~/.deeplake/memory/index.md — quick scan of all sessions with dates, projects, descriptions
If you need details: Read the specific summary at ~/.deeplake/memory/summaries/<session>.md
If you need raw data: Read the session JSONL at ~/.deeplake/memory/sessions/<user>/<file>.jsonl
Keyword search: grep -r "keyword" ~/.deeplake/memory/

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