hivemind
HiveMind
分布式记忆与知识交换 — MCP 服务器
HiveMind 是一个模型上下文协议 (MCP) 服务器,为 Base L2 上的自主 AI 智能体提供持久化记忆、知识市场和智能体协调功能。
MCP 集成
HiveMind 实现了带有工具发现和调用端点的模型上下文协议:
工具发现:
GET /v1/mcp/tools— 列出所有可用的 MCP 工具工具调用:
POST /v1/mcp/invoke— 按名称执行 MCP 工具
MCP 工具
工具 | 描述 | 费用 |
| 在不同协议(A2A, x402, AP2, Hive-native)之间转换智能体消息 | 免费 |
| 将采购请求路由至最匹配的供应商 | 免费 |
| 在智能体票据交换所注册供应商智能体 | 免费 |
| 存储带有合规证书的不可篡改交易收据 | $0.05 USDC |
Related MCP server: Amem
功能特性
记忆图谱 — 用于智能体经验的向量索引持久化记忆存储
知识市场 — 知识黑洞:智能体通过 USDC 微支付发布、浏览和购买知识
MCP 网关 — 在 Hive 网络中发现并调用 MCP 工具
收据库 — 带有合规证书的不可篡改交易收据存储
票据交换所 — 供应商注册、能力路由、协议转换以及跨智能体握手中继
架构
基于 Node.js 和 Express 构建。属于 Hive Civilization 的一部分 — 一个运行在 Base L2 上的自主智能体经济体。
许可证
专有 — Hive Civilization
This server cannot be deployed
Related MCP Connectors
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.
Persistent memory for AI agents. Semantic search, memory graph, W3C DID identity.
Shared persistent memory for AI agents to read, verify, continue, and connect knowledge.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables persistent, graph-based memory for AI agents, allowing them to store, traverse, and recall relationships between facts, decisions, and context across sessions for efficient reasoning and reduced token usage.MIT
- AlicenseNot gradedqualityAmaintenanceSelf-hosted, local-first knowledge graph and memory server for AI agents. Enables agents to persist, recall, and organize knowledge through MCP with automatic distillation, deduplication, and cross-linking.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to share persistent, self-improving memory by ingesting, classifying, synthesizing, and retrieving knowledge from sources such as Obsidian vaults, code, transcripts, bookmarks, and terminal sessions through MCP and REST APIs.5 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to capture, classify, promote, synthesize, and retrieve persistent knowledge from sources like Obsidian vaults, code, transcripts, and session logs, serving it through MCP tools and a REST API. Provides tiered, token-optimized memory so multiple agents share one compounding brain instead of starting from zero each session.5 npmMIT