activeloopai/hivemind

Hivemind

One brain for all your agents

Auto-learning, cloud-backed shared brain for Claude Code • OpenClaw • Codex • Cursor • Hermes • pi • Claude Cowork (Alpha) agents.

One engineer's agent figures out a tricky migration on Monday.

> Tuesday, every agent on the team can execute the pattern.

On LoCoMo, the public long-context memory benchmark, Hivemind is 25% cheaper, 1.7× fewer tokens, and 31% fewer turns than running without shared memory. (See the numbers below.)

Beyond memory. Hivemind doesn't just remember. It mines your team's traces for repeated patterns and codifies them into reusable skills that propagate back into every agent on the team. The agent your junior engineer used this morning is sharper because of what your senior engineer's agent figured out last week.

• 📥 Captures every session's prompts, tool calls, and responses as structured traces in Deeplake
• 🧠 Codifies patterns into reusable SKILL.md files, available to every agent on your team
• 🔍 Searches traces and skills with hybrid lexical + semantic retrieval (ILIKE lexical fallback when embeddings off)
• 🔗 Propagates capability across sessions, agents, teammates, and machines in real time
• 📁 Intercepts file operations on ~/.deeplake/memory/ through a virtual filesystem backed by SQL
• 📝 Summarizes sessions into AI-generated wiki pages via a background worker at session end
• ☁️ BYOC: keep data in your own GCS, Azure, S3, or on-prem bucket. See Security & storage

Benchmarks

On the LoCoMo long-context memory benchmark (100 QA pairs, Claude Haiku via claude -p, hybrid lexical + semantic retrieval), Hivemind cuts cost, tokens, and turns versus a no-memory baseline:

| Metric | Baseline | Hivemind | Improvement | |-------------------|----------|----------|------------------| | Cost / 100 QA | $8.94 | $6.65 | 25% cheaper | | Tokens / question | 1,700 | 1,008 | 1.7× fewer | | Turns / question | 8.9 | 6.2 | 31% fewer |

The agent reaches the answer in fewer turns with less context, because the prior work is already in scope at recall time, not re-derived per session.

Quick start

One command, all your agents.

macOS / Linux

curl -fsSL https://deeplake.ai/hivemind.sh | sh

Windows — in PowerShell:

irm https://deeplake.ai/hivemind.ps1 | iex

Any platform, via npm — for CI and Dockerfiles, or where policy blocks piping a downloaded script to a shell. Skips the checks the installers do, so Node 22+ and a writable npm prefix are on you:

npm i -g @deeplake/hivemind && hivemind install

The installer detects every supported assistant on your machine (table below), wires up the hooks, and shows a one-line consent prompt before opening a browser for sign-in. Restart your assistants after install.

Headless / CI installs: pass an API token instead of using the browser flow:

HIVEMIND_TOKEN= hivemind install
or
hivemind install --token 

Get a token from your account settings on https://deeplake.ai. With no token in a non-interactive shell, the install completes with hooks but skips sign-in; run hivemind login later to enable shared memory.

Install for a specific assistant only:

hivemind install --only claude
hivemind claude install    # equivalent
hivemind codex install
hivemind claw install
hivemind cursor install
hivemind hermes install
hivemind pi install
hivemind claude_cowork install   # Alpha

Check what's wired up:

hivemind status

Supported assistants:

| Platform | Integration | Auto-capture | Auto-recall | |------------------|--------------------------------------------------|--------------|-------------| | Claude Code | Marketplace plugin | ✅ | ✅ | | OpenClaw | Native extension | ✅ | ✅ | | Codex | Hooks (hooks.json) | ✅ | ✅ | | Cursor | Hooks (hooks.json 1.7+) | ✅ | ✅ | | Hermes Agent | Shell hooks (config.yaml) + skill + MCP server | ✅ | ✅ | | pi | Extension API (pi.on(...)) + skill + AGENTS.md | ✅ | ✅ | | Claude Cowork 🅰️ | MCP server (Claude Desktop) | 🅰️ Alpha¹ | ✅ |

🅰️ Claude Cowork is Alpha. Auto-recall (the hivemind_search / read / index tools) is solid. ¹Auto-capture covers Local Agent Mode sessions only — those write a transcript we can tail; plain desktop-chat turns leave no readable local trace and aren't captured (why).

Alternative install paths

/plugin marketplace add activeloopai/hivemind
/plugin install hivemind
/reload-plugins
/hivemind:login

openclaw plugins install clawhub:hivemind

Fetch and follow instructions from https://raw.githubusercontent.com/activeloopai/hivemind/main/harnesses/codex/INSTALL.md

git clone https://github.com/activeloopai/hivemind.git ~/.codex/hivemind
~/.codex/hivemind/harnesses/codex/install.sh

Hooks need review
2 hooks are new or changed.
Hooks can run outside the sandbox after you trust them.
1. Review hooks
 › 2. Trust all and continue
   3. Continue without trusting (hooks won't run)

hivemind cursor install

hivemind hermes install

hivemind pi install

Claude Cowork (Alpha)

Claude Cowork is Anthropic's agentic assistant inside the Claude Desktop app. It has no hook lifecycle like the other agents — it only talks to Hivemind through MCP — so the integration works differently and ships as Alpha.

hivemind claude_cowork install

This registers the shared MCP server (~/.hivemind/mcp/server.js) under mcpServers.hivemind in Claude Desktop's claude_desktop_config.json. Fully quit and reopen Claude Desktop to load it.

Recall (stable). Cowork gains hivemind_search, hivemind_read, and hivemind_index — the same shared memory every other agent reads. On the first tool use per host, a one-time data-collection notice is prepended to the result.

Auto-capture (Alpha) — how it works. With no SessionStart/Stop hooks to capture from, the MCP server runs a background ingester that tails Cowork's Local Agent Mode transcripts (~/Library/Application Support/Claude/local-agent-mode-sessions//.claude/projects//.jsonl). For each new line it writes a row to the sessions table with agent="claude_cowork" (user prompts, assistant messages, tool calls + results), de-duplicated by a per-transcript line watermark. When a transcript has been idle for 5 minutes it is treated as finished, and the same wiki-worker / skillify workers every other agent uses run for it (summary tagged claude_cowork → it shows up in hivemind_index).

Known limitation. Only Local Agent Mode** sessions (where Cowork opens its sandbox/agent and works) write a transcript we can read. Plain desktop-chat turns are not captured: by MCP design a server never sees the conversation (only the tool calls the model makes), and the chat itself lives in Anthropic's cloud + a compressed claude.ai IndexedDB cache with no supported read surface. Capturing those would need an official Anthropic export/hook.

Uninstall

hivemind uninstall              # remove from every detected assistant
hivemind codex uninstall        # remove from one

How it works

Capture → Codify → Propagate → Compound. Every coding-agent interaction (prompt, tool call, response) is captured as a structured trace in Deeplake. A background worker mines traces for repeated patterns and codifies them into SKILL.md files, scoped to your workspace. Codified skills propagate into every Hivemind-connected agent's context at inference time. The agent your junior engineer used this morning is sharper because of what your senior engineer's agent figured out last week.

Features

🔍 Natural search

Just ask your agent naturally:

"What was Emanuele working on?"
"Search traces for authentication bugs we've solved"
"What did we decide about the API design?"
"Show me skills my team has codified for handling migrations"

🔒 Privacy controls

Disable capture entirely:

HIVEMIND_CAPTURE=false claude

Disable capture for a specific directory tree (persistent, travels with the repo) by dropping a .hivemind file with { "collect": false }. See Per-directory config.

Enable debug logging:

HIVEMIND_DEBUG=1 claude

⚠️ Data collection notice

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 | The agent's final response | | Subagent activity | Subagent tool calls and responses | | Codified skills | Patterns extracted from traces |

All users in your Deeplake workspace can read this data. That's the design. Shared capability requires shared substrate. A DATA NOTICE is displayed at the start of every session. Workspace-level isolation prevents data leakage between orgs.

Configuration

| Variable | Default | Description | |---------------------------|---------------------------|--------------------------------------------| | HIVEMIND_TOKEN | _(none)_ | API token (auto-set by login) | | HIVEMIND_ORG_ID | _(none)_ | Organization ID (auto-set by login) | | HIVEMIND_WORKSPACE_ID | default | Workspace name or id (hivemind workspaces) | | HIVEMIND_API_URL | https://api.deeplake.ai | API endpoint | | HIVEMIND_TABLE | memory | SQL table for summaries and virtual FS | | HIVEMIND_SESSIONS_TABLE | sessions | SQL table for per-event session capture | | HIVEMIND_MEMORY_PATH | ~/.deeplake/memory | Path that triggers interception | | HIVEMIND_CAPTURE | true | Set to false to disable capture | | HIVEMIND_CAPTURE_ONLY_CLI | _(none)_ | Set to true to capture only interactive CLI sessions. Sessions spawned by the Claude Agent SDK (Python/TypeScript) are skipped; their CLAUDE_CODE_ENTRYPOINT is sdk-py / sdk-ts, so they fail the substring check for cli. | | HIVEMIND_SKILLIFY_EVERY_N_TURNS | 20 | Assistant turns between auto skill-mining attempts. Lower = more frequent mining (cheaper sessions, noisier output); higher = fewer attempts on longer histories. | | HIVEMIND_SUMMARY_EVERY_N_MSGS | 50 | Captured events between periodic session summaries. The first summary of a session runs at 10 events regardless. Raise it to cut background summary runs. | | HIVEMIND_SUMMARY_EVERY_HOURS | 2 | Time-based summary cadence, used when at least one new event has arrived since the last summary. | | HIVEMIND_WIKI_WORKER | _(none)_ | Set to 1 to disable the background session-summary worker entirely (no claude -p summary runs). Also set automatically inside the worker as a recursion guard. Capture and recall keep working. | | HIVEMIND_GRAPH_ON_STOP | _(none)_ | Set to 0 to disable the code-graph rebuild that runs on Stop / SessionEnd. | | HIVEMIND_EMBEDDINGS | _(none)_ | Read once, when ~/.deeplake/config.json has no embeddings.enabled yet: unset or false seeds it off, any other value (true, 1, ...) seeds it on. Afterwards only hivemind embeddings install/enable (persist on) and disable/uninstall (persist off) change it. | | HIVEMIND_DEBUG | _(none)_ | Set to 1 for verbose hook debug logs |

Per-directory config (.hivemind)

The variables above set one global identity for the whole machine. A .hivemind file lets a specific directory tree override that: either route it to a different org/workspace, or opt out of capture entirely.

Routing is symmetric — a routed directory both writes its traces to that workspace and reads memory from it. Sessions started under it search, recall, and browse ~/.deeplake/memory in the routed workspace, and hivemind whoami reports it.

Drop a .hivemind JSON file at the root of the tree you want to configure:

{
  "orgId": "acme-corp",
  "workspaceId": "client-work",
  "collect": true
}

| Field | Effect | |---------------|-------------------------------------------------------------------------------| | orgId | Route this tree to this org — captured traces and memory reads. | | workspaceId | Route to this workspace. | | collect | false → never capture traces from this tree. Reads still route. |

Any field may be omitted; omitted fields fall back to your global identity.

orgId / workspaceId are identity (they apply to reads and writes alike); collect is a capture switch (writes only). The two are independent, which is what makes the read-only recipe below work.

Three common recipes:

// route this repo to a client org/workspace — reads and writes both land there
{ "orgId": "acme-corp", "workspaceId": "client-work" }
// never collect traces from this folder (e.g. a personal or sensitive repo)
{ "collect": false }
// read a shared workspace's memory, but never write to it
{ "workspaceId": "client-work", "collect": false }

Routing never carries a token — auth stays in ~/.deeplake/credentials.json, so a .hivemind only ever takes effect against orgs your existing login already authorizes. An HIVEMIND_ORG_ID / HIVEMIND_WORKSPACE_ID set in your environment wins over a .hivemind for that field; hivemind whoami discloses which one is in effect.

Committed vs local

Two filenames are recognized, mirroring the .env / .env.local convention every dev already knows:

| File | Commit it? | For | |------|-----------|-----| | .hivemind | Yes (like .editorconfig) | The repo declaring where its traces belong (or that it's off-limits). Teammates who clone inherit it. | | .hivemind.local | No (gitignore it) | Your personal override or opt-out, not imposed on teammates. Wins over .hivemind in the same directory. |

There's nothing to hide: a .hivemind can't carry a token (see below), so committing one is safe. It just declares intent. Use .hivemind.local only when a choice is yours alone (add it to your repo's .gitignore, like .env.local).

A copy-ready template lives at .hivemind.example. Run cp .hivemind.example .hivemind and edit. (The .example file is inert; Hivemind only reads .hivemind and .hivemind.local.)

How it resolves

When a session starts, Hivemind walks up from the working directory (cwd, its parent, its grandparent, and so on) and uses the first file it finds (a .hivemind.local beats a .hivemind in the same directory). Nearest wins; ancestors above it are ignored. This is the .git/.gitconfig model, not .gitignore-style merging. There is no inheritance: a leaf file that wants both its parent's org and its own workspace must state both.

~/work/.hivemind           { "orgId": "acme-corp" }
~/work/client/.hivemind    { "workspaceId": "sensitive", "collect": false }
session in ~/work/client/svc/  →  uses client/.hivemind ONLY
                                  (collect:false wins; the org above is NOT inherited)
session in ~/work/other/       →  no .hivemind found → global identity

Precedence is the conventional env > file > login: an explicitly-set HIVEMIND_ORG_ID / HIVEMIND_WORKSPACE_ID overrides a .hivemind routing value (that field is left untouched), which in turn overrides your logged-in default. collect: false is a fail-safe opt-out and is always honored.

Safety: routing is disclosed, not hidden

Because a .hivemind travels with a rep