Vector Mirror runs on your own machine — the client starts it, so there is no endpoint to ping. 32 installs a week from npm. Last commit 12 Jun 2026.
Deterministic SVG perception for LLM agents — measures, never guesses. MCP server.
Today is the operative word: we check Vector Mirror every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 vector-mirror -- npx -y vector-mirror
{
"mcpServers": {
"vector-mirror": {
"args": [
"-y",
"vector-mirror"
],
"command": "npx"
}
}
}
[mcp_servers.vector-mirror]
command = "npx"
args = ["-y", "vector-mirror"]
{
"mcpServers": {
"vector-mirror": {
"args": [
"-y",
"vector-mirror"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"vector-mirror": {
"args": [
"-y",
"vector-mirror"
],
"command": "npx"
}
}
}
Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.
AI-powered vector knowledge graph MCP server for agents. Supports add node, add edge, semantic node
Local-first RAG engine with MCP server for AI agent integration.
Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth
Local-first memory for coding agents — MCP server, single SQLite file, local embeddings
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
Answers built from our own checks of this server.