Ross ROSS = Recommend OSS · open-source software intelligence for agents

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 observed · 2026-08-28

github.com/basicmachines-co/basic-memory · homepage · Python · AGPL-3.0 (copyleft) observed · 2026-08-28

Health v2 · maintenance only

84/100

  • Activity 99
  • Release rhythm 87
  • Longevity 45
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 1
  • age_days: 639
  • days_rel: 8
  • days_push: 8
  • n_releases_24m: 90

Full methodology

Adoption not part of the score

3769 stars · 262 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

service · maturity active

mcp rag search-engine markdown chatbot large-language-models developer-tools privacy self-hosted python cli cross-platform self-hosted mcp-server ai-memory local-first knowledge-graph obsidian semantic-search zettelkasten claude privacy-first knowledge-management ai-agents docker

9 sources

Member repositories

RepositoryRoleHealth v2
basicmachines-co/basic-memorymain84

For agents

markdown · JSON · MCP: product_card(name="basicmachines-co/basic-memory")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem