HiveMind

Peer-to-peer shared memory for AI agents. When one agent learns something, every other agent on every machine can use it too. Local-first, no cloud, no central server.

Website: hivemind.projectmentor.org · Docs: docs/ · For developers: hivemind.projectmentor.org/dev · Security: SECURITY.md · Changes: CHANGELOG.md · Best practices: docs/WORKING_TOGETHER.md · Current agent contract: 4.2 (hv version)

The HiveMind dashboard, hdash dash. Watch the intro video on the site.

HiveMind gives your AI agents a shared hive. They read it and write in it. Old lines stay. A fact earns confidence, which means trust, when different agents agree on their own. An agent cannot raise that trust by repeating itself. A decision can later get a score from what happened after you made it. Each device keeps the whole hive. The devices copy new lines to each other over Tailscale, a private network between your devices.

Pinecone, Weaviate, LlamaIndex, and LangGraph help one program search a pile of text. HiveMind keeps the notes your agents share, and a record of who agreed.

---

What you get

• Copies itself. When one agent learns something, the other devices get a copy. They talk over Tailscale, a private network. They send only the new notes.
• Trust is earned. A fact becomes more trusted when different agents agree on their own. Saying it again does not help. Agents on one device count for less than agents on different devices. A new device can read. It can add notes after you admit it. You admit it with hive-mind group admit. If two notes disagree, you see both.
• No boss device. Every device keeps the full hive. The notes only grow. They fit together when the devices meet again. The owner is the person who says who may write. If that owner key is lost, the devices you already admitted can pick a new owner.
• Learns from what happened. A decision can name the facts it used. When you write down how that decision turned out, the decision gets an outcome score. Those facts get a utility score. An agent can hint that a note is important. The score rises when other agents point at it. A guess is an idea. An idea is not a fact until other agents agree.
• Works offline. An agent keeps going with no network. The new notes join the rest when the device is online again.
• Search stays on your device. hv search looks through the notes on that machine. You can sort by trust, by importance, by utility, or by how new the note is. The search does not call out to the internet.
• Little to run. You do not set up a database or a cloud account. After the devices are in sync, one device's hive is the whole memory. A backup is a copy of the files.
• You can look back. Every fact says who wrote it and when. Old lines stay in the hive.
• Works with agents you already have. Claude Code, Hermes, and Claude Desktop (through a local MCP server). Any agent that can run a command can use hv.

---

Best practices

Several AI agents can share one project. Give each agent one job, or the same agent will grade their own homework.