Telys — on-device memory runs on your own machine — the client starts it, so there is no endpoint to ping. 131 installs a week from pypi.
Private on-device memory & retrieval for AI assistants — offline vector + lexical search.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
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 telys -- uvx telys
{
"mcpServers": {
"telys": {
"args": [
"telys"
],
"command": "uvx"
}
}
}
[mcp_servers.telys]
command = "uvx"
args = ["telys"]
{
"mcpServers": {
"telys": {
"args": [
"telys"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"telys": {
"args": [
"telys"
],
"command": "uvx"
}
}
}
Team engineering memory for AI coding assistants. 47 MCP tools, pgvector semantic search.
MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.
Persistent memory and knowledge graph for AI assistants — keyword + vector + graph search.
Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
Graph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.
Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.
File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
Persistent memory and vector search for AI agents. Hosted, OAuth-protected via Google sign-in.
Answers built from our own checks of this server.