Cloud-backed persistent shared memory for AI agents powered by Deeplake
How to install hivemind?
activeloopai/hivemind
$git clone https://github.com/activeloopai/hivemindInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install hivemind by running `git clone https://github.com/activeloopai/hivemind`, then use it for the current task and follow its documentation at https://github.com/activeloopai/hivemind.
README.md
| 1 | <h1 align="center"> |
| 2 | <br> |
| 3 | <a href="https://github.com/activeloopai/hivemind"> |
| 4 | <img src="https://raw.githubusercontent.com/activeloopai/hivemind/main/docs/public/hivemind-logo.svg" alt="Hivemind" width="120"> |
| 5 | </a> |
| 6 | <br> |
| 7 | Hivemind |
| 8 | <br> |
| 9 | </h1> |
| 10 | |
| 11 | <h4 align="center">One brain for all your agents</h4> |
| 12 | |
| 13 | <p align="center"> |
| 14 | <a href="https://www.npmjs.com/package/@deeplake/hivemind"><img src="https://img.shields.io/npm/v/@deeplake/hivemind?color=blue&label=npm&style=for-the-badge" alt="npm"></a> |
| 15 | <a href="https://github.com/activeloopai/hivemind/stargazers"><img src="https://img.shields.io/github/stars/activeloopai/hivemind?style=for-the-badge&logo=github" alt="GitHub stars"></a> |
| 16 | <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg?style=for-the-badge" alt="License"></a> |
| 17 | <a href="package.json"><img src="https://img.shields.io/badge/node-%3E%3D22.0.0-brightgreen.svg?style=for-the-badge" alt="Node"></a> |
| 18 | <a href="https://deeplake.ai"><img src="https://img.shields.io/badge/Powered%20by-Deeplake-orange.svg?style=for-the-badge" alt="Deeplake"></a> |
| 19 | <a href="https://www.ycombinator.com"><img src="https://img.shields.io/badge/Y%20Combinator-backed-ff6600.svg?style=for-the-badge" alt="Y Combinator backed"></a> |
| 20 | <a href="https://join.slack.com/t/hubdb/shared_invite/zt-35zr0yil0-lnzJcQhACsBlB7~3lufrCg"><img src="https://img.shields.io/badge/Slack-chat-4A154B?logo=slack&logoColor=white&style=for-the-badge" alt="Join us on Slack"></a> |
| 21 | </p> |
| 22 | |
| 23 | <p align="center"> |
| 24 | Auto-learning, cloud-backed shared brain for <b>Claude Code • OpenClaw • Codex • Cursor • Hermes • pi • Claude Cowork (Alpha)</b> agents.<br> |
| 25 | </p> |
| 26 | |
| 27 | <p align="center"> |
| 28 | <a href="https://trendshift.io/repositories/28172" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/repositories/28172" alt="activeloopai/hivemind | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a> |
| 29 | </p> |
| 30 | |
| 31 | > One engineer's agent figures out a tricky migration on Monday. |
| 32 | > |
| 33 | > Tuesday, every agent on the team can execute the pattern. |
| 34 | |
| 35 | On [LoCoMo](https://arxiv.org/abs/2402.17753), 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.](#benchmarks)) |
| 36 | |
| 37 | <p align="center"> |
| 38 | <img src="https://raw.githubusercontent.com/activeloopai/hivemind/main/docs/public/hivemind_cursor_readme_banner_dark.png" alt="Cut Cursor spend by 34% with Hivemind" width="100%"> |
| 39 | </p> |
| 40 | |
| 41 | **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. |
| 42 | |
| 43 | - 📥 **Captures** every session's prompts, tool calls, and responses as structured traces in Deeplake |
| 44 | - 🧠 **Codifies** patterns into reusable `SKILL.md` files, available to every agent on your team |
| 45 | - 🔍 **Searches** traces and skills with hybrid lexical + semantic retrieval (BM25 fallback when embeddings off) |
| 46 | - 🔗 **Propagates** capability across sessions, agents, teammates, and machines in real time |
| 47 | - 📁 **Intercepts** file operations on `~/.deeplake/memory/` through a virtual filesystem backed by SQL |
| 48 | - 📝 **Summarizes** sessions into AI-generated wiki pages via a background worker at session end |
| 49 | - ☁️ **BYOC**: keep data in your own GCS, Azure, S3, or on-prem bucket. [See Security & storage](#security--storage) |
| 50 | |
| 51 | ## Benchmarks |
| 52 | |
| 53 | On the [LoCoMo](https://arxiv.org/abs/2402.17753) 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: |
| 54 | |
| 55 | | Metric | Baseline | Hivemind | Improvement | |
| 56 | |-------------------|----------|----------|------------------| |
| 57 | | Cost / 100 QA | $8.94 | $6.65 | **25% cheaper** |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
