cogvault runs on your own machine — the client starts it, so there is no endpoint to ping. 155 installs a week from pypi. Last commit 14 Oct 2026.
Local hybrid-search memory for AI agents over plain Markdown. Multi-tenant, offline, no LLM.
What the code does
We read the source, 4 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
subprocess.run([chrome, "--headless=new", "--disable-gpu", "--hide-scrollbars",
with open(os.path.join(OUT, f"{name}-{theme}.svg"), "w") as f:
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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 cogvault -- uvx cogvault{
"mcpServers": {
"cogvault": {
"command": "uvx",
"args": [
"cogvault"
]
}
}
}[mcp_servers.cogvault]
command = "uvx"
args = ["cogvault"]{
"mcpServers": {
"cogvault": {
"command": "uvx",
"args": [
"cogvault"
]
}
}
}{
"servers": {
"cogvault": {
"type": "stdio",
"command": "uvx",
"args": [
"cogvault"
]
}
}
}Optional settings from the registry entry, left out of the block above:
COGVAULT_MODEL (Embedding model override; otherwise .cogvault.toml in the tenant, then the multilingual default), COGVAULT_LOG (Recall log: 'off' to disable, or a path to relocate the JSONL log).
Alternatives to cogvault
same job, measured the same wayMarkdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.
Durable agent memory over a markdown vault: bitemporal facts, timelines, hybrid graph search.
Long-term memory for AI agents: local-first PKM with provenance and hybrid search.
Persistent memory for AI agents: Markdown entries, hybrid search, typed graph links
Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
Local hybrid keyword + vector search (SQLite FTS5 + sqlite-vec) over markdown vaults and code.
Local memory server for AI agents: hybrid search, a fact graph and a hash-chained audit log.
Local Markdown/Obsidian knowledge substrate for MCP agents with governed memory and hybrid search.
cogvault — questions
Answers built from our own checks of this server.