Hivemind

io.github.QuantuLabsPublished by GitHub account QuantuLabsv0.1.3Updated Oct 24, 2026

Query multiple AI models (OpenAI, Anthropic, Google) for consensus responses.

VerifiedSTDIODesktop onlyDeveloper ToolsAI & ML

Overview

AI-generated overview

Queries OpenAI, Anthropic and Google models together and returns a synthesized consensus answer, with tools to configure keys and track usage.

What you can do
  • Query several AI models at once and get a synthesized consensus answer, with optional multi-round refinement.
  • Set and check API keys and active providers, and toggle grounding search and other settings.
  • Review token usage and cost statistics for past queries.
  • In Claude Code, run slash commands to orchestrate consensus, configure keys and view stats, or enable automatic fallback consultation when the host model is stuck.
When to use it
Useful when you want a second and third opinion on a hard question, or higher-confidence answers than a single model gives, especially inside Claude Code where Claude can orchestrate and synthesize the other models' replies.
Requirements
Runs locally as an npm package (Node.js 18 or newer) over stdio. Needs at least one API key, OpenAI or Google AI, supplied via OPENAI_API_KEY or GOOGLE_API_KEY or entered through the configure_keys tool or a config file. An Anthropic key is optional for non-Claude-Code clients. Network access to the model providers is required.
Before you install
Requires paid third-party API keys, and every query spends money on the configured providers; usage and cost statistics are exposed for tracking. Keys are stored on the machine through the configuration tool or a config file, so protect that file. Questions and context are sent to OpenAI, Google and optionally Anthropic.

Installation

In SourceWeft

  1. Open Hivemind in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Hivemind

[License: MIT] [npm version]

Multi-model AI consensus platform that queries GPT-5.2, Claude Opus 4.5, and Gemini 3 Pro simultaneously to deliver synthesized, high-confidence responses.

MCP Server for Claude Code

Use Hivemind directly in Claude Code to get perspectives from GPT-5.2 and Gemini 3 Pro. Claude acts as the orchestrator and synthesizes the responses.

Requirements

Note: No Anthropic API key needed - Claude is already your host!

Installation

bash
npm install -g @quantulabs/hivemindclaude mcp add hivemind -- hivemind

Configuration

You need at least one API key, but both are recommended for better consensus:

Option 1: Paste directly (recommended)

bash
/hive-config sk-proj-xxx...   # OpenAI key/hive-config AIzaSy...        # Google key

Option 2: Config file

Create ~/.config/hivemind/.env:

bash
OPENAI_API_KEY=sk-...GOOGLE_API_KEY=AIza...
# Optional: Override default modelsOPENAI_MODEL=gpt-5.1GOOGLE_MODEL=gemini-2.5-flash

A .env.example template is included in the package.

Using with other MCP clients (non-Claude Code)

For standalone MCP usage, you can also add an Anthropic key to include Claude in the consensus:

bash
ANTHROPIC_API_KEY=sk-ant-...

Disable Claude Code mode via /hive-config > Settings > Claude Code Mode.

Usage

bash
/hive "Why is my WebSocket connection dropping?"

Claude orchestrates the consensus from GPT-5.2 and Gemini 3 Pro responses.

Available Tools

ToolDescription
hivemindQuery models and get synthesized consensus
configure_keysSet API keys (stored securely)
check_statusCheck configuration and active providers
configure_hiveToggle grounding search and settings
check_statsView token usage and cost statistics

Claude Code Commands

  • /hive <question> - Orchestrate multi-model consensus with Claude as the synthesizer
  • /hive-config - Configure API keys and settings
  • /hivestats - View usage statistics

Automatic Hivemind Fallback

Copy CLAUDE.md.example to your project's .claude/CLAUDE.md to enable automatic Hivemind consultation when Claude is stuck (after 3+ failed attempts).

Prompt Caching

All providers use optimized caching for cost reduction on follow-up queries:

ProviderTypeSavingsMin Tokens
OpenAIAutomatic50%1024
Gemini 2.5+Implicit90%-
AnthropicExplicit90%1024

Web Interface

A full-featured web app with solo mode, hivemind mode, and conversation history.

Quick Start

bash
# Clone the repositorygit clone https://github.com/QuantuLabs/hivemind.gitcd hivemind
# Install dependencies (requires Bun >= 1.0)bun install
# Start development serverbun dev

Open http://localhost:3000, click the settings icon, and enter your API keys.

Features

  • Multi-Model Consensus: Query 3 leading AI models simultaneously
  • Deliberation Algorithm: Up to 3 rounds of refinement to reach consensus
  • Solo Mode: Chat with individual models (GPT, Claude, Gemini)
  • Hivemind Mode: Get synthesized responses from all models
  • Conversation History: Persistent chat sessions
  • Dark/Light Theme: Full theme support
  • Secure Storage: API keys encrypted with AES-GCM in browser

Security

  • API keys are encrypted using AES-GCM with PBKDF2 key derivation
  • Keys are stored locally in browser localStorage (never sent to servers)
  • Session persistence uses sessionStorage (cleared on browser close)

How Consensus Works

  1. Initial Query: All 3 models receive the same question
  2. Analysis: An orchestrator analyzes responses for agreements/divergences
  3. Refinement: If no consensus, models see other perspectives and refine (up to 3 rounds)
  4. Synthesis: Final response synthesizes agreed points and addresses divergences

Supported Models

OpenAI

  • GPT-5.2 (default)
  • GPT-5.1, GPT-5, GPT-5 Mini, GPT-5 Nano
  • O4 Mini

Anthropic

  • Claude Opus 4.5 (default)
  • Claude Sonnet 4.5, Claude Opus 4, Claude Sonnet 4

Google

  • Gemini 3 Pro (default)
  • Gemini 3 Flash, Gemini 2.5 Pro/Flash/Flash Lite, Gemini 2.0 Flash

Project Structure

hivemind/├── apps/│   └── web/              # Next.js 14 frontend├── packages/│   ├── core/             # Shared consensus logic & providers│   └── mcp/              # Model Context Protocol server└── .claude/              # Claude Code integration

Development

bash
# Run all testsbun test
# Run tests with coveragebun test:coverage
# Build all packagesbun build
# Lint codebun lint

License

MIT

Developed by QuantuLabs

Source: README.md at commit b74985c

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.3LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts