Changelog
Shipped, fixed, and improved
Every 1AIVault release, straight from the release notes that ship with the product.
SHIPPED · v1.13.0
Shared Memory, Clear Conflicts
New
- **Share selected memories with your team** — Point 1AIVault at a folder in a Git repo you already trust, then publish hand-picked memories for teammates to pull into their own vaults
- **Find duplicate and contradicting memories** — A new Conflicts view in Classify scans your vault locally for near-duplicates, opposing claims, and overlapping notes
- **Import the memory each AI tool already keeps on this machine** — Scan Claude Code auto-memory, Claude Code's global notes, Gemini, Codex, Qwen, OpenCode, Amp, and Windsurf memory files in one pass through Bring Your Memory
Improved
- **Connect Claude Desktop from the Microsoft Store on Windows** — 1AIVault now finds the Store build's config location and can install or repair the vault connection there as well as classic installs
- **Clearer agent setup messages on Windows** — When OpenCode's install left only a placeholder binary, or when a tool answers slowly, the Agents panel explains what is wrong and how to fix it
- **Easier feedback from About** — Send a bug or feature request from Settings → About, or email support directly
Fixed
- Fixed **Claude Desktop connection missing the Microsoft Store install on Windows** — the vault now targets the config the Store build actually uses, and repairs every detected install type when both are present
- Fixed **AI tools that print a version but never fully exit** being reported as timed out — tools that answered with a real version are now treated as installed
- Fixed **Cursor conversation paths being misread on Windows** — Cursor imports resolve the correct data folders again
SHIPPED · v1.12.2
Windows AI tools stay available, and macOS live imports keep running
Fixed
- Codex, Cline and Qwen no longer show an error when they work in PowerShell — the Agents panel finds the working Windows installation and keeps it available for Chat and classification
- OpenCode no longer stays unavailable after an earlier installation problem — the Agents panel finds the working copy automatically instead of returning to the broken one
- 1AIVault no longer closes during live imports on macOS — conversations from Claude Code, Codex, Cursor, Cline, Gemini, OpenCode, Antigravity, Grok and Hermes keep importing in the background
SHIPPED · v1.12.1
Tidy Up Topics, more reliable AI-tool connections, and Windows fixes
New
- Tidy Up Topics: a new eraser button clears topics left empty after you reclassify or delete their memories, so your topic list only shows topics that still hold something
Improved
- Connect to more AI tools reliably — the vault's MCP connection is now named 'oneaivault' instead of '1aivault' (some clients reject a name starting with a number); existing setups update themselves on the next install or repair across Claude Desktop, Claude Code, Cursor, Cline, Codex, Gemini, Grok, OpenCode, and Hermes
- Open large topic lists instantly — topics load in pages, with Load more and Load all to pull in the rest
- Cleaner Claude Code imports — slash-command echoes, local command output, and setup notes are left out of your memories
Fixed
- Windows: no more window flash or error on Claude Code hooks; AI tools no longer fail to launch with a Node error; OpenCode no longer misread as unavailable; slow tools like Hermes no longer misreported as timed out; each tool's real version is read correctly
- Empty '0 entries' topics are cleared automatically; junk topics like 'Project Control' are no longer created from Claude Code setup notes
SHIPPED · v1.12.0
Encrypted cross-device vault sync and task-ready Focus Briefs
New
- Sync Across Devices
- Focus Briefs
- Evidence-Aware Memory
Improved
- Watch scheduled automation live, with status, AI messages, thinking, and tool activity, then open the memories a run classified
- Take control of active schedules — stop, safely stop and delete, or clear failed runs while keeping successful history
- Read more useful Dream diaries, with a clear action, affected memory, and reason for every applied change
Fixed
- Fixed AI tools installed through PowerShell not being found on Windows
- Fixed meaning-based recall failing to start on Windows
- Fixed one unavailable AI tool hiding other installed clients
SHIPPED · v1.11.0
Memory That Thinks — Watch Your AI Recall, and Let Your Vault Dream
New
- **See every memory your AI tools look up** — A new Neuron screen records each search your connected AI tools run against the vault and lets you replay it, so you can finally answer "did my AI actually use my memory, and why did it pick that one?"
- **Recall that understands meaning, not just words** — Searching now finds the right memory even when you phrase the question completely differently from how the memory was written
- **Nothing to set up** — Recall improvements are on from the start and work quietly in the background; you can turn semantic recall or route tracing off anytime in Settings
SHIPPED · v1.8.1
A focused update that makes links, file paths, and scheduled Claude Code classification safer and more reliable.
New
- Link and File Actions
Fixed
- Fixed **links replacing the vault with a blank or unusable page** — clicking a link in memory details now keeps 1AIVault open and gives you safe actions instead
- Fixed **scheduled classification with Claude Code failing to reach the vault** — unattended schedules can find the required memory tools and save classifications again
New
- Train a Personal Memory Model — fine-tune a compact local model on your memories, entirely on your machine (Apple Silicon Macs), and ask it questions about your own knowledge offline.
- Pick what it learns: your whole vault, selected topics, or a recent time window — with a preview of how many memories are in scope and roughly how many training examples they produce.
- Secrets stay out — API keys, tokens, and private keys are detected and redacted before a single training example is written, with a pre-scan that shows what will be hidden.
Improved
- A brand-new startup experience — the app opens instantly on an animated 1AIVault logo, then fades into a fully-loaded Dashboard with no white flash or half-drawn screens.
- Large vaults stay smooth — heavy background work (statistics, activity heatmaps, memory linking, tier promotion, conversation capture) now runs off the app's hot path.
- Faster Dashboard and sidebar on big vaults — counts and stats load in the background instead of competing with what you're doing.
Fixed
- Fixed the app freezing with a spinning cursor for several seconds after launch on large vaults.
- Fixed a light-theme flash at launch for dark-theme users — the window now opens in your theme from the first frame.
- Fixed the app briefly showing your vault before the unlock screen when Vault Lock is enabled.
New
- **Improve messy memories into clean ones** — A new Improve queue finds related, repeated, and near-duplicate memories and helps you consolidate them into one clear memory, a reusable skill, or a cleanup plan
- **Let your AI tools suggest improvements** — Claude Code, Cursor, Codex, and other connected clients can propose a cleanup mid-conversation; proposals wait in the queue for your review and never change the vault on their own
- **Export memory as a shareable pack** — Bundle a curated set of memories and skills into a single pack file you can hand to a teammate or reuse on another machine
Improved
- **Smarter, more relevant recall** — Memory search returns tighter, better-ranked results across large vaults
- **Faster top-bar search previews** — Previewing matching memories from the global search field feels quicker and clearer
Fixed
- Fixed **"Open improve queue" and other shortcuts opening the wrong tab** — deep links from the Dashboard and Memory Reads now land on the Connection tab they name instead of falling back to Install MCP
SHIPPED · v1.6.0
Redesigned vault, more MCP clients, better Classify controls
New
- Neural Vault Interface - See the vault through a redesigned Dashboard, global search, activity heatmap, and consistent app surfaces.
- More AI Tool Connections - Install 1AIVault MCP for GitHub Copilot, Roo Code, Qoder, Trae, Factory Droid, Kilo Code, Warp, and Augment, with Cline CLI support across import, chat, and classify.
- Deeper Classify Control - Review forgotten memory, remember or clean up hidden items, rebuild classifications from scratch, and merge topics with selected entries.
Improved
- Choose classification context size for bulk classification and save the preferred default.
- Classification prompts inspect more context when needed and include confidence for every assignment.
- Collect separates browser-extension captures, on-machine imports, and other supported tools.
Fixed
- Cline MCP connection finds current Cline installs and repairs stale Cline connections more reliably.
- Unified Chat renders Cline CLI replies as readable messages instead of raw event output.
- Forgotten tab search can find hidden entries without restoring them to normal vault results.
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
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
SHIPPED · v1.4.0
Auto-Inject Memory
New
- Auto-Inject Memory
- Claude Code Fresh Starts
Improved
- Safer instruction file updates — 1AIVault manages only its own memory block and preserves the rest of each AI tool's instruction file
- Hand-edited memory blocks are protected — If you manually change an injected block, 1AIVault skips the next rewrite instead of overwriting your edits
- Clearer injection status — Each tool row now shows whether memory is off, injected, handled by Claude Code's fresh-start option, or skipped because of a manual edit
Fixed
- Fixed **new memories saved from AI clients not reaching auto-injected context until restart** — memories saved through connected AI tools now refresh into enabled memory blocks while 1AIVault is running
SHIPPED · v1.3.2
Sharper, Faster Recall
Improved
- Much faster memory recall — Searching, browsing recent memories, opening a tag, and exploring related memories now complete in a fraction of the steps, so results come back noticeably quicker on larger vaults
- Smarter search ranking — A match in a memory's title now outranks the same word buried deep in its body, so the most relevant memory surfaces first
- Leaner search results — AI clients now receive a short preview of each matching memory and pull the full text only when they need it, keeping recall fast and responsive
Fixed
- Fixed **AI clients coming up empty when searching vaults with large saved conversations** — when a memory held a full saved conversation, search results grew too large and got cut off before the useful memories came through. Searches now return compact previews so the right memories always reach Claude Desktop, Claude Code, Cursor, and Cline — and the full text of any memory can still be pulled on demand
10 older 1AIVault releases are listed in the release history.