Hivemind Shared Memory Skills
Recall team knowledge and connect agent work to persistent goals and a knowledge graph.
Activeloop’s Hivemind package combines shared Deeplake memory with goal tracking and graph workflows, while its worker captures traces and codifies recurring patterns.
Use cases
- Recover decisions and patterns from earlier sessions
- Track goals and explore connected team knowledge
How to use
Install the complete upstream Hivemind runtime for the chosen harness and configure Deeplake access. The selected Claude Code directory contains the full memory, goals, and graph group; other harness directories are adaptations.
Skills
hivemind-goals
Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/. Use whenever the user mentions a goal, objective, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to", "fix X", or any actionable work item — the goal system replaced the legacy `hivemind tasks` CLI and now covers both objectives and tasks.
activeloopai/hivemindhivemind-graph
Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user asks structural questions about the codebase — "what calls X?", "what does Y import?", "where is Z defined?", "what's the architecture / which subsystems exist?", "what's the impact of changing this?". The graph is an AST-derived map of the repo, queried as files (no build needed — it rebuilds automatically).
activeloopai/hivemindhivemind-memory
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
activeloopai/hivemind