Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by projectmentor · MCP Server · ★ 56
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is hive-mind safe to install? View the security audit →
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: · For developers: hivemind.projectmentor.org/dev The HiveMind dashboard, hv dash. Watch the intro video on the site. HiveMind is a shared, append-only memory that your AI agents read and write as they work. Facts, decisions, and outcomes accumulate over time and earn trust through independent corroboration, not by an agent asserting it. Each machine holds the full memory and syncs directly with its peers over your private Tailscale network. There is no server to operate and nothing leaves your hardware. It is not a vector database or a RAG framework. It is the memory-and-trust layer your agents share s
| Stars | 56 |
| Forks | 3 |
| Language | Python |
| Category | MCP Server |
| License | AGPL-3.0 |
| Quality Score | 72.9223427139466/100 |
| Open Issues | 22 |
| Last Updated | 2026-10-03 |
| Created | 2026-06-03 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~16k |
Looking for a hive-mind alternative? If you're comparing hive-mind with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
📜 An MCP server for conversation history search and retrieval in Claude Code
High-value AI skills repository for Codex, Claude Code, OpenClaw, agents, prompts, and automation workflows.
Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live upd
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
MCP server for YouTube — search videos, get transcripts, channels, and playlists. Works with Claude, Cursor &
A lightweight persistent-memory companion for OpenCode & Claude
Explore other popular mcp server tools:
hive-mind is Persistent institutional shared memory as observable middleware for collaborative AI agents. It is categorized as a MCP Server with 56 GitHub stars.
hive-mind is primarily written in Python. It covers topics such as agent-memory, agentic, ai.
You can find installation instructions and usage details in the hive-mind GitHub repository at github.com/projectmentor/hive-mind. The project has 56 stars and 3 forks, indicating an active community.
hive-mind is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to hive-mind on Agent Skills Hub include claude-historian-mcp, Commonly-used-high-value-skills, montycat-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: