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.
npx -y skills add activeloopai/hivemind --skill hivemind-memory --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
juliusbrussee/caveman
mattpocock/skills
shadcn/improve
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills