By activeloopai
Persist, read, write, and share memory across Claude Code sessions and agents using cloud-backed Deeplake storage. Automatically track lifecycle events like session starts, prompts, tool uses, and ends via Python hooks to maintain stateful workflows.
npx claudepluginhub activeloopai/hivemind --plugin hivemindPersistent memory for Claude Code — memories survive across sessions, projects, and machines
Persistent cloud memory for Claude Code. Auto-loads memories on session start, auto-saves on stop, with on-demand store/recall skills.
Persistent memory for AI coding agents -- captures tool usage, compresses via LLM, injects context into future sessions. 12 hooks, 41 MCP tools, 4 skills, real-time viewer.
Persistent agent memory that survives across sessions — auto-compacting 3-tier memory with hybrid search. Your agent remembers what it learned, decided, and built.
Long-term semantic memory for Claude Code, powered by OpenViking. Auto-recall relevant memories at session start and capture important information during conversations.
Matches all tools
Hooks run on every tool call, not just specific ones
Share bugs, ideas, or general feedback.
Persistent, cloud-backed shared memory for AI agents.
Captures everything. Recalls anything. Shares across sessions, teammates, and machines.
~/.deeplake/memory/ through a virtual filesystem backed by SQL| Platform | Status | Install |
|---|---|---|
| Claude Code | ✅ Stable | See Quick start |
| OpenClaw | 🔧 Beta | See Quick start |
| Codex | 🔜 Coming soon | — |
Add the marketplace:
/plugin marketplace add activeloopai/hivemind
Install the plugin:
/plugin install hivemind
Reload plugins:
/reload-plugins
Log in:
/hivemind:login
That's it. Your agents now share a brain.
The plugin auto-updates on each session start. To manually update:
/hivemind:update
Install from ClawHub (Telegram, TUI, WhatsApp):
openclaw plugins install hivemind
Send a message. The plugin sends you an auth link. Click, sign in, done.
┌─────────────────────────────────────────────────────────────┐
│ Your AI Agent │
└──────────────────────────┬──────────────────────────────────┘
│
┌──────────────────▼──────────────────┐
│ 📥 Capture (every turn) │
│ prompts · tool calls · responses │
└──────────────────┬──────────────────┘
│
┌──────────────────▼──────────────────┐
│ 🧠 Hivemind Cloud │
│ SQL tables · BM25 search │
│ shared across all agents │
└──────────────────┬──────────────────┘
│
┌──────────────────▼──────────────────┐
│ 🔍 Recall (before each turn) │
│ search memory · inject context │
└─────────────────────────────────────┘
Every session is captured. Every agent can recall. Teammates in the same org see the same memory.
Just ask Claude naturally:
"What was Emanuele working on?"
"Search memory for authentication bugs"
"What did we decide about the API design?"
After each session, a background worker generates a wiki summary: key decisions, code changes, next steps. Browse them at ~/.deeplake/memory/summaries/.
Invite teammates to your Deeplake org. Their agents see your memory, your agents see theirs. No setup, no sync, no merge conflicts.
Disable capture entirely:
DEEPLAKE_CAPTURE=false claude
Enable debug logging:
DEEPLAKE_DEBUG=1 claude
This plugin captures session activity and stores it in your Deeplake workspace:
| Data | What's captured |
|---|---|
| User prompts | Every message you send |
| Tool calls | Tool name + full input |
| Tool responses | Full tool output |
| Assistant responses | Claude's final response |
| Subagent activity | Subagent tool calls and responses |
All users in your Deeplake workspace can read this data. A DATA NOTICE is displayed at the start of every session.
Automatic long-term memory for Claude Code via Hindsight. Recalls relevant memories before each prompt and retains conversation transcripts after each response.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim