#2222nd of 27 in Memory

basic-memory

MCP server that stores AI memory as Markdown notes with a knowledge graph

Documentation ↗ Website ↗ Repository on GitHub ↗

Stars: 4.5k
License: AGPL-3.0
Last commit: Nov 2026
Last release: Oct 2026
Language: Python

Missed the latest GitHub check; these facts may be older.

Overview

Basic Memory is a Python MCP server that lets Claude, Codex, Cursor, ChatGPT and other MCP clients read and write structured Markdown notes on your disk. Notes use observations and wikilink relations that form a traversable graph, indexed in local SQLite (or Postgres) with hybrid full-text and vector search. A hosted cloud edition is sold separately; the local version is free.

Who it is for: Users of Claude, Codex or Cursor who want persistent, file-based memory

Strengths

Notes are plain Markdown files, editable in Obsidian or any editor, with two-way sync
Hybrid full-text and vector search via FastEmbed, with optional cross-encoder reranking
MCP tools carry read-only/destructive/idempotent hints; works with Claude, Codex, Cursor, VS Code
Ships Claude Code, Hermes and OpenClaw plugins plus shared skills from the same repo

Weaknesses

AGPL-3.0 license may be a problem for embedding in proprietary products
Install needs uv and the --prerelease=allow flag due to a FastMCP 4 pre-release dependency
Built-in cross-device sync and mobile access are in the paid cloud; local needs Git or Syncthing
Reranking is off by default and adds latency plus a first-run model download

What it needs

no GPU
Docker + Compose
Needs Python 3.12+, uv, SQLite (default) or Postgres, Milvus (optional), LiteLLM (optional)
Models: Any MCP client (Claude, Codex, Cursor, VS Code, ChatGPT), FastEmbed embeddings, jinaai/jina-reranker-v1-tiny-en reranker

Also in Memory

See all 27

Also in Memory
Rank	Project	Score
1	hindsightAgent memory server with retain, recall and reflect operations60.6k stars+12,039 (+25%) in 30 daysMIT	95 out of 100
2	gbrainMemory store with sources and a knowledge graph for coding agents32.7k stars+2,034 (+6.6%) in 30 daysMIT	91 out of 100
3	MemPalaceLocal verbatim memory store for AI agents with semantic search and MCP60.5k starsMIT	90 out of 100
#4	SupermemoryMemory and context engine for AI agents, with user profiles and hybrid search31.6k starsMIT	89 out of 100
#5	Mem0Long-term memory layer that stores and retrieves user facts for LLM agents Live demo ↗ (opens in a new tab)68.9k starsApache-2.0	88 out of 100

How to choose

Check what gets stored (raw messages, extracted facts, graphs) and how it is retrieved.
Multi-tenant isolation matters if several users or agents share one store.
Look at the backing store (Postgres, a vector DB, a graph DB) and whether you already run it.

Health

Releases: Not checked
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

AGPL-3.0 Copyleft

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes, with source

Your part: Like GPL-3.0, and if users reach a changed version over a network, offer them its source under AGPL-3.0.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

Set it up

Needs before it works: Python 3.12+, uv, SQLite (default) or Postgres, Milvus (optional), LiteLLM (optional).

Bring in an engineer who knows basic-memory. By the hour for upkeep and fixes, or a fixed price for a build. Our own engineering service; it never changes a rank.

Where to run it

RackNerd ↗ (opens in a new tab)Budget KVM VPS from $26.99 a year to run Docker apps yourself.
RepoCloud ↗ (opens in a new tab)One-click hosting for about 890 open-source apps, each on its own VPS.

Referral links: if you sign up through one, we get a commission. They never change a rank.

Ask your AI assistant

The rankings as an MCP server for Claude, Cursor, ChatGPT and any MCP client. Free, no key, read-only.

Setup for other apps

Claude Codeclaude mcp add archestack -- npx -y @archestack/mcp

Connector URLhttps://mcp.archestack.com/mcp

Then ask: Compare basic-memory with its top alternatives on Archestack

#22 of 27 in Memory on Archestack, as of 12 Nov 2026.

Show it in your README or on your site

The badge below goes in a README; a card with the rank, score and signals goes on a site or blog. Both update twice a day.

Show code

README (Markdown)

[![Archestack](https://archestack.com/badge/basicmachines-co/basic-memory.svg)](https://archestack.com/best-of-ai/projects/basic-memory/)

Site or blog (HTML)

<iframe src="https://archestack.com/embed/best-of-ai/basic-memory/" title="basic-memory on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

How badges work Preview the card

Best of Open-Source AI on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with basic-memory filled in.

Chat and assistants

Agents and MCP

RAG, search and memory

Voice

Image and video

Workflows

Coding with AI

Apps and SaaS

Models and ML

Security

Learning

By field