# basicmachines-co/basic-memory

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

Repository: https://github.com/basicmachines-co/basic-memory
Canonical: https://ross.abutalabs.com/products/basic-memory
Homepage: https://basicmemory.com
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: ai, claude, llm, mcp, open-source, python, obsidian, obsidian-md, knowledge-management, knowlege-graph, local-first, markdown, privacy-first, privacy-first-ai, productivity
Last push: 2026-08-25T20:43:52+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 45
- inputs: {"age_days": 639, "days_push": 8, "days_rel": 8, "gap_med": 1, "n_releases_24m": 90}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3769, forks 262 (observed 2026-08-28T04:08:18.086001+00:00)

## What it is
Basic Memory is an open-source, local-first MCP server that gives AI assistants persistent memory as a knowledge graph of plain Markdown files you own. It indexes notes with full-text, semantic, and graph search, and syncs with tools like Claude, ChatGPT, Cursor, and Obsidian via the Model Context Protocol.

## Use cases
- give my AI assistant persistent memory across sessions
- store project context so I never re-explain it to Claude
- build a knowledge graph in Markdown that AI can read and write
- add semantic search to my Obsidian-style notes
- share a team knowledge base with AI agents
- keep AI memory local and private instead of vendor-owned

## When to choose
- you want AI memory stored as plain, inspectable Markdown files you own
- you use MCP-compatible clients like Claude, ChatGPT, Cursor, or Codex
- you need local-first, privacy-focused knowledge management
- you want semantic and knowledge-graph search over your notes

## When to avoid
- you need a fully managed turnkey solution without any setup (though a paid cloud tier exists)
- you require a non-AGPL license for commercial embedding
- you don't use any MCP-compatible AI tools

## Facets
- artifact type: service
- maturity: active
- function: mcp, rag, search-engine, markdown, chatbot
- domain: large-language-models, developer-tools, privacy, self-hosted
- platform: python, cli, cross-platform, self-hosted
- tags: mcp-server, ai-memory, local-first, knowledge-graph, obsidian, semantic-search, zettelkasten, claude, privacy-first, knowledge-management, ai-agents, docker

## Member repositories
- basicmachines-co/basic-memory (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:18.086001+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:27:53.854720+00:00, confidence not recorded.
  - readme: https://github.com/basicmachines-co/basic-memory (fetched 2026-08-28T04:08:18.086001+00:00, sha 801a5dde1673)
  - homepage: https://basicmemory.com (fetched 2026-08-29T09:22:48.840841+00:00, sha e8f2f3fe3492)
  - site_page: https://basicmemory.com/features (fetched 2026-08-29T09:22:48.850098+00:00, sha 2158d672bb43)
  - site_page: https://basicmemory.com/docs (fetched 2026-08-29T09:22:48.854024+00:00, sha 3d8b618ab8aa)
  - site_page: https://basicmemory.com/about (fetched 2026-08-29T09:22:48.856096+00:00, sha a4253f420603)
  - site_page: https://docs.basicmemory.com (fetched 2026-08-29T09:22:48.859562+00:00, sha 7e89fead1f4d)
  - registry_pypi: https://pypi.org/pypi/basic-memory/json (fetched 2026-08-29T09:22:48.861219+00:00, sha 4e3524ca0c68)
  - site_page: https://basicmemory.com/pricing (fetched 2026-08-29T09:22:48.851971+00:00, sha 33fa4d0934de)
  - site_page: https://basicmemory.com/for (fetched 2026-08-29T09:22:48.857928+00:00, sha 2b7145d82289)
- Data as of 2026-08-30T08:39:29.467469+00:00.