Memory Fabric runs on your own machine — the client starts it, so there is no endpoint to ping. 215 installs a week from pypi. Last commit 14 Oct 2026.
File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
What the code does
We read the source, 3 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.
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.
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 memory-fabric -- uvx memory-fabric{
"mcpServers": {
"memory-fabric": {
"command": "uvx",
"args": [
"memory-fabric"
]
}
}
}[mcp_servers.memory-fabric]
command = "uvx"
args = ["memory-fabric"]{
"mcpServers": {
"memory-fabric": {
"command": "uvx",
"args": [
"memory-fabric"
]
}
}
}{
"servers": {
"memory-fabric": {
"type": "stdio",
"command": "uvx",
"args": [
"memory-fabric"
]
}
}
}Alternatives to Memory Fabric
same job, measured the same wayShared memory + orchestration for your coding agents. Local-first MCP, vector RAG.
Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.
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
Memory for AI assistants in one SQLite file: full-text search, no vectors, no embeddings.
Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.
Memory Fabric — questions
Answers built from our own checks of this server.