Hashgrid DNA (local) runs on your own machine — the client starts it, so there is no endpoint to ping. 1 549 installs a week from pypi. Last commit 23 Oct 2026.
Search that learns from feedback, over text and images: embeds locally, sends DNA only vectors.
Nothing serious here today
Today is the operative word: we check Hashgrid DNA (local) every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
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 sdk -- uvx hashgrid{
"mcpServers": {
"sdk": {
"command": "uvx",
"args": [
"hashgrid"
]
}
}
}[mcp_servers.sdk]
command = "uvx"
args = ["hashgrid"]{
"mcpServers": {
"sdk": {
"command": "uvx",
"args": [
"hashgrid"
]
}
}
}{
"servers": {
"sdk": {
"type": "stdio",
"command": "uvx",
"args": [
"hashgrid"
]
}
}
}Optional settings from the registry entry, left out of the block above:
HASHGRID_API_KEY (Your DNA API key, hg-…. Leave it out and the create_grid tool makes a grid and saves its key in the local index), HASHGRID_EMBEDDER (The embedder, one per grid: fastembed:<model> (local; fastembed:Qdrant/clip-ViT-B-32 for images), openai:<model> or voyage:<model>), OPENAI_API_KEY (For an openai:<model> embedder), VOYAGE_API_KEY (For a voyage:<model> embedder), HASHGRID_INDEX (The local index: a sqlite file that maps DNA ids to your text).
Alternatives to Hashgrid DNA (local)
same job, measured the same wayA search engine that learns from feedback, over embeddings: one tool per API route.
Search and SQL on object storage: full-text, vector and hybrid search plus SQL over your data.
Local hybrid keyword + vector search (SQLite FTS5 + sqlite-vec) over markdown vaults and code.
Generate and vectorize clean, editable SVG graphics from text, images, or both.
Memory for AI assistants in one SQLite file: full-text search, no vectors, no embeddings.
Federated local-first search across transcripts, files, KG, vectors and the web for AI agents.
Graph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.
Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.
Hashgrid DNA (local) — questions
Answers built from our own checks of this server.