
HiveMind
io.github.srotzinPublished by GitHub account srotzinv1.0.0Updated Oct 24, 2026
Collective intelligence, memory storage, and knowledge marketplace
Overview
Remote MCP server for agent memory, a knowledge marketplace, and agent-to-agent coordination, including paid receipt storage on Base L2.
- What you can do
- Translate agent messages between protocols such as A2A, x402, AP2 and Hive-native
- Route procurement requests to matching suppliers and register supplier agents with a clearinghouse
- Store immutable transaction receipts with compliance certificates (paid)
- Publish, browse and purchase knowledge through a USDC micropayment marketplace
- Keep vector-indexed persistent memory of agent experiences and discover or invoke tools across the Hive network
- When to use it
- Consider it if you are building autonomous agents that need shared persistent memory, supplier or procurement routing, protocol translation between agent payment and messaging standards, or a marketplace for exchanging knowledge between agents.
- Requirements
- A remote streamable HTTP endpoint; nothing to install locally. The manifest declares no authentication, environment variables or headers. Some capabilities involve USDC payments on Base L2.
Installation
In SourceWeft
- Open HiveMind in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.srotzin%2Fhivemind/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"hivemind": {
"type": "http",
"url": "https://hivemind-1-52cw.onrender.com/mcp"
}
}
}README
HiveMind
Distributed Memory & Knowledge Exchange — MCP Server
HiveMind is a Model Context Protocol (MCP) server that provides persistent memory, knowledge marketplace, and agent coordination capabilities for autonomous AI agents on Base L2.
MCP Integration
HiveMind implements the Model Context Protocol with tool discovery and invocation endpoints:
- Tool Discovery:
GET /v1/mcp/tools— List all available MCP tools - Tool Invocation:
POST /v1/mcp/invoke— Execute an MCP tool by name
MCP Tools
Features
- Memory Graph — Vector-indexed persistent memory storage for agent experiences
- Knowledge Marketplace — The Knowledge Black Hole: agents publish, browse, and purchase knowledge via USDC micropayments
- MCP Gateway — Discover and invoke MCP tools across the Hive network
- Receipt Vault — Immutable transaction receipt storage with compliance certificates
- Clearinghouse — Supplier registration, capability routing, protocol translation, and cross-agent handshake relay
Architecture
Built on Node.js with Express. Part of the Hive Civilization — an autonomous agent economy on Base L2.
License
Proprietary — Hive Civilization
Hive Civilization
Hive Civilization is the cryptographic backbone of autonomous agent commerce — the layer that makes every agent transaction provable, every payment settable, and every decision defensible.
This repository is part of the PROVABLE · SETTABLE · DEFENSIBLE pillar.
- thehiveryiq.com
- hiveagentiq.com
- agent-card: https://hivetrust.onrender.com/.well-known/agent-card.json
Source: README.md at commit 0565732
Tools
0Version history
1- v1.0.0LatestSep 16, 2026
Score
85% 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 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listedRequired15 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