hubmesh runs on your own machine — the client starts it, so there is no endpoint to ping. 814 installs a week from pypi. Last commit 5 Aug 2026.
Deterministic multi-hop graph retrieval for RAG. Zero LLM calls in the query path.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add hubmesh -- uvx hubmesh
{
"mcpServers": {
"hubmesh": {
"args": [
"hubmesh"
],
"command": "uvx"
}
}
}
[mcp_servers.hubmesh]
command = "uvx"
args = ["hubmesh"]
{
"mcpServers": {
"hubmesh": {
"args": [
"hubmesh"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"hubmesh": {
"args": [
"hubmesh"
],
"command": "uvx"
}
}
}
Deterministic SVG perception for LLM agents — measures, never guesses. MCP server.
Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.
Repository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.
Private on-device memory & retrieval for AI assistants — offline vector + lexical search.
Agentic memory for cyber threat intelligence. STIX graphs, actor aliasing, offline RAG, Sigma/YARA.
Local-first personal knowledge base. Cited answers from your vault via vector + graph retrieval.
Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG.
Built-in MCP server for ArcadeDB multi-model database (graph, document, vector, time-series)
Answers built from our own checks of this server.