Memory Fabric runs on your own machine — the client starts it, so there is no endpoint to ping. 586 installs a week from pypi. Last commit 6 Sep 2026.
File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
We read the source, 19 h ago · rules 3dff92dd89df
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.
proc = subprocess.run(
for skill_md in sorted(skills_dir.rglob("SKILL.md")):
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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 memory-fabric -- uvx memory-fabric
{
"mcpServers": {
"memory-fabric": {
"args": [
"memory-fabric"
],
"command": "uvx"
}
}
}
[mcp_servers.memory-fabric]
command = "uvx"
args = ["memory-fabric"]
{
"mcpServers": {
"memory-fabric": {
"args": [
"memory-fabric"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"memory-fabric": {
"args": [
"memory-fabric"
],
"command": "uvx"
}
}
}
Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.
Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.
Team engineering memory for AI coding assistants. 47 MCP tools, pgvector semantic search.
Local-first memory for coding agents — MCP server, single SQLite file, local embeddings
Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.
Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.
MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.
Answers built from our own checks of this server.