Loreweave runs on your own machine — the client starts it, so there is no endpoint to ping. 167 installs a week from npm. Last commit 9 Oct 2026.
Durable agent memory over a markdown vault: bitemporal facts, timelines, hybrid graph search.
Nothing serious here today
Today is the operative word: we check Loreweave 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 loreweave -- npx -y loreweave{
"mcpServers": {
"loreweave": {
"command": "npx",
"args": [
"-y",
"loreweave"
]
}
}
}[mcp_servers.loreweave]
command = "npx"
args = ["-y", "loreweave"]{
"mcpServers": {
"loreweave": {
"command": "npx",
"args": [
"-y",
"loreweave"
]
}
}
}{
"servers": {
"loreweave": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"loreweave"
]
}
}
}Alternatives to Loreweave
same job, measured the same wayLocal hybrid-search memory for AI agents over plain Markdown. Multi-tenant, offline, no LLM.
Durable memory for AI agents: fact extraction, hybrid retrieval, temporal graph. SQLite/Postgres.
Git-backed org memory for AI agents — hybrid search, tables, files & a URI graph over MCP.
Persistent memory for AI agents: Markdown entries, hybrid search, typed graph links
Persistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.
Company brain for AI agents — temporal knowledge graph search, exploration, and durable memory.
Local memory server for AI agents: hybrid search, a fact graph and a hash-chained audit log.
Agent-native knowledge OS on Markdown: typed graph, hybrid search, and compiler over MCP.
Loreweave — questions
Answers built from our own checks of this server.