Store
Sign in

SHIPPED · v1.5.0

v1.5.0 - Faster recall, forget controls, and Antigravity support

New

  • Forget and Remember

  • Antigravity CLI Support

  • Faster Live Capture

Improved

  • Much faster recall on large vaults — Search results now stay compact, show the relevant part of each memory, and avoid sending full saved conversations unless an AI tool asks for them

  • Better memory ranking — Recent and frequently used memories get stronger placement, pinned memories remain first, and tag matches are now searchable

  • Smarter related memory — Related-memory lookups and project-scoped injected context can include nearby memories that use different wording when semantic recall is enabled

  • Smoother live imports — Claude Code, Codex, Cursor, OpenCode, and Antigravity do less repeat work while watching active conversation folders, so busy setups feel more responsive

  • Claude Code session continuity — Resumed and compacted Claude Code sessions stay connected to their original thread so one logical conversation is easier to recall

  • Stronger auto-injected briefs — New session context now includes recent work and classification gaps, skips forgotten memory, and better tells AI tools when to search, save, import, or classify

  • Clearer Connection guidance — Auto-Inject now shows context freshness, classification gaps, and import coverage so you can refresh what your AI tools know before starting a session

  • Faster app navigation — Heavy screens such as Chat, Skills, Collect, Classify, Connection, Settings, command palette, and update dialog load only when opened

  • Better Classify workspace — Resize the entry list, open entry details fullscreen, and use cleaner AI tool logos while sorting through large vaults

Fixed

  • Fixed **tag searches missing tagged-only memories** — entries now appear when the matching word is in a tag, even if it is not in the memory body

  • Fixed **search previews starting at the beginning of long conversations** — previews now jump to the matching part of the memory so results are easier to choose

  • Fixed **AI searches causing needless instruction file rewrites** — searching from connected clients no longer refreshes auto-injected files when no memory content changed

  • Fixed **large transcript imports slowing down linking** — long raw conversations skip low-value per-entry linking while useful tag-based connections still build in the background

  • Fixed **deleted local transcripts disturbing saved vault memory** — when an AI tool cleans up its own conversation files, existing vault entries stay available

  • 1AIVault memory entry detail view showing the Forget entry toolbar action that hides one saved memory from search, topics, imports, MCP reads, and injected context.
    1AIVault memory entry detail view showing the Forget entry toolbar action that hides one saved memory from search, topics, imports, MCP reads, and injected context.
  • 1AIVault topic classification view showing the Forget topic action for hiding a topic and its timeline from normal memory reuse.
    1AIVault topic classification view showing the Forget topic action for hiding a topic and its timeline from normal memory reuse.
  • forget entry
    forget entry
  • forget topic
    forget topic