Basic Memory
What's New

v0.21.0

Basic Memory Teams support — shared cloud workspaces that work consistently across MCP and CLI, plus faster search and sync and smarter Markdown parsing in v0.21.

v0.21.0 brings Basic Memory Teams support: shared cloud workspaces now work consistently across every MCP tool and CLI command, so your AI assistant reaches the right projects whether you're working solo or with a team. Search and sync are also noticeably faster, with smarter, more predictable Markdown parsing.

Heads up: relation parsing fix. Unquoted multi-word text before a wikilink used to be misread as a custom relation type. That's fixed — but if you intentionally relied on multi-word relation types, quote them before upgrading so they survive the next re-sync. See Upgrading below.

Basic Memory Teams Support

This is our first release to include support for Basic Memory Teams (subscription required). When you work with Teams, your projects live in a shared cloud workspace that everyone on the team can read and write. If you have a local workspace or personal Basic Memory subscription you can continue to use both at the same time.

What you'll notice:

  • Cross-workspace project discovery in MCP — your assistant's project list now spans every accessible cloud workspace, not just the current one.
  • bm project list spans all workspaces — no more missing projects depending on which workspace you were in.
  • Create projects by workspace slug from MCP — create_memory_project(workspace=...) targets a specific cloud workspace directly.
  • bm project add --visibility — set visibility for cloud projects at creation time.

See the Teams guide for inviting members, roles, and seats.

Faster Search and Sync

  • Search hydration no longer issues an N+1 query — results come back faster, especially on large knowledge bases.
  • File indexing is batched during sync, and single-file sync is significantly quicker.
  • Vector sync does less redundant work, with tuned embedding defaults.

No configuration changes required — existing projects just get faster on upgrade.

Recent Activity

recent_activity orders by updated_at, so notes you just edited bubble to the top. When there are more results than fit in a response, a footer tells you so you know to page for the rest.

Search Scope and Totals

  • Search across all your projects. search_notes stays scoped to the resolved project by default; pass the new search_all_projects=True parameter to search every project at once.
  • Search responses include result totals, so paginated clients can stop guessing how many matches exist.

CLI Quality of Life

  • bm orphans lists entities with no relations — handy for finding notes that aren't yet linked into your knowledge graph.
  • bm reset is now guarded — it refuses to run while a basic-memory mcp process is alive (use --force to override in automation), so a reset can no longer corrupt an open session.
  • bm reindex rebuilds search indexes and vector embeddings without dropping the database.
  • bm project info reports cloud index freshness; private projects show their display name instead of a raw UUID.

Training-Data-Friendly Tool Aliases

MCP tools now accept the parameter names models reach for naturally — q / search / text as aliases for query, and similar across other tools. Assistants spend fewer turns correcting argument names, so common operations just work on the first try.

Smarter Parsing

  • Obsidian callouts are recognized as callouts — > [!note] blocks stay out of your observations.
  • Long relation type names are fully supported.
  • Prose before a wikilink is parsed as a plain link rather than a relation type — see Upgrading for the details.

Upgrading

Relation parsing fix (#824). Unquoted multi-word text before a wikilink used to be misread as a custom relation type. Now it's parsed correctly:
  • Bare list wikilinks like - [[Target]] index as links_to.
  • Prose list items like - some other thing [[Target]] index as links_to.
  • Single-token relation types are unaffected: relates_to [[Target]] still works.
If you intentionally used multi-word relation types, quote them before upgrading so they survive the next re-sync: "relates to" [[Target]] or 'relates to' [[Target]].

Search, sync, and routing improvements apply automatically with no configuration changes.

Patch releases: v0.21.1 was a CI-only release for Homebrew formula tooling. v0.21.2 through v0.21.4 followed with local/cloud routing, external-client write_note, and CLI startup stability fixes. v0.21.5 adds workspace/project routing follow-ups: duplicate cloud project rows stay distinct in MCP project lists, cloud write_note responses return workspace-qualified permalinks, and SQLite vector reindexing handles sqlite-vec tables safely.

Documentation

For commit-level release history, see Changelog.

Basic Memory Teams

Share a cloud workspace with your team — invite members, assign roles, and build one knowledge base together.

Hermes Plugin

Give Hermes Agent persistent Basic Memory — search-before-answer recall, auto-capture, and 10 agent tools.