April 2026

Introduces a referral program for earning credits, Linear OAuth in managed mode, cleaner thinking blocks rendered as markdown and collapsed by default, configurable PKB injection, an overhauled API key management gateway, a polished chat and sidebar experience, and broad stability fixes.

• Referral program: a new Earn Credits referral system lets users share a unique referral link and earn credits when friends sign up, accessible from the Billing settings tab and the preferences drawer with a gift icon CTA, featuring a modal with how-it-works steps, referral stats, copy-to-clipboard link, dynamic per-referral and total cap amounts, and program terms, with full dark mode support
• Linear integration: Linear OAuth now supports managed mode, allowing users to connect to Linear through the platform without configuring their own OAuth app, enabled by default during onboarding alongside Outlook
• Thinking blocks rendered as markdown and collapsed by default: AI reasoning output on macOS is now rendered as full markdown and always starts collapsed, making responses cleaner and easier to skim, with additional performance gains from caching parsed markdown segments to avoid redundant work on every render
• Configurable PKB injection via _autoinject.md: Personal Knowledge Base injection is now controlled through an _autoinject.md file, with fixes for duplicate injection across turns, incorrect interleaving inside memory blocks, and more accurate deduplication through text normalization
• Overhauled API key management: a new async gateway API for reading and writing keys replaces direct disk access across settings, UI components, and voice services, improving reliability and security
• Chat and sidebar experience improvements: a new animated typing indicator, spell checking in the composer, a new Recents group replacing ungrouped conversations, fixes for oversized greeting fonts, doubled placeholder suggestions, sidebar text truncation, and suppressed unread indicators for automated threads
• Stability and correctness fixes: numerous fixes across scroll geometry, history reloading, dictation, audio tap handling, remote feature flag polling, and OAuth flows, reducing crashes, infinite loops, and stale-data issues throughout the app

Introduces the Personal Knowledge Base for reliable fact recall, a refreshed design system with new colors and typography, major macOS chat performance fixes, an expanded subagent system with roles and inter-agent communication, and numerous stability and rendering improvements.

• Personal Knowledge Base (PKB) introduced: Vellum now includes a reliable fact-recall system that files and retrieves important information across conversations, with improved memory extraction, deduplication, edit-history tracking, and a fully redesigned Memory inspector UI featuring compact list views, confidence bars, color-coded indicators, and an inline detail panel
• Refreshed design system with new colors and typography: the entire color palette has been updated from warm moss and olive tones to a cooler blue-grey neutral scale, typography has been switched from DM Sans to Inter, and components across the app — buttons, cards, toggles, segment controls, settings, and sidebar — have been updated to match the new Figma design tokens for a cleaner, more polished look
• Major chat performance improvements: several significant hangs and layout bottlenecks in the macOS app have been resolved, including a 465-second conversation-switch freeze, a 118-second LazyVStack layout cascade, and recurring main-thread stalls caused by SwiftUI Observation cascades, Combine dispatch, and GeometryReader overhead
• Subagent system expanded with roles, tool scoping, and inter-agent communication: subagents now support typed roles with per-role tool allowlists, a new notify_parent tool for communicating results back to a parent agent, label-based lookup as an alternative to UUIDs, and a file_list core tool for directory listing within subagent contexts
• Numerous stability and rendering fixes across macOS: fixes include real-time streaming thinking blocks, preserved thinking block expansion state, improved markdown italic and emphasis rendering, better Anthropic prompt cache utilization with an append-only history approach, corrected sidebar pinned conversation display, and more reliable scroll and layout behavior throughout the app

The biggest release yet — Vellum goes open source, introduces platform-hosted assistants, a completely revamped memory system with multimodal support, Outlook feature parity, conversation folders, and the new Heartbeat system for proactive assistant check-ins.

• Open source launch: The Vellum Assistant repository is now publicly available, inviting the community to explore, contribute, and build on the platform
• Platform-hosted assistants: Assistants can now run fully hosted on the Vellum platform, removing the need for local infrastructure and enabling seamless cloud-based operation
• Revamped memory system with multimodal support: The memory graph has been completely overhauled with image references, multimodal embeddings, event-dated memories, hybrid dense/sparse search for recall, and smarter injection and consolidation — replacing the legacy memory items table entirely
• Outlook Calendar and Email reach full feature parity with Google: Outlook Calendar and Outlook Email integrations are now generally available, matching the functionality previously available only for Google Calendar and Gmail
• Conversation folders and sidebar improvements: A full conversation groups/folders system has been introduced, with system groups seeded on first launch, source-based subgrouping, improved icons and count badges, and a polished delete group flow
• Heartbeat — proactive assistant check-ins: The new Heartbeat system enables the assistant to periodically review its scratchpad, reflect on recent conversations, and proactively reach out when it has something worth sharing — now enabled by default
• Skills API redesign: Skills have been refactored with a new kind/origin/status model, unified search across all skill registries, improved install paths, and better handling of capability nodes including seeding, pruning, and injection ordering
• Performance and stability improvements across macOS and iOS: Caching visible conversations and paginated messages to eliminate multi-second hangs, moving expensive operations off the main thread, caching NSImage instances and font warmup, and adding Equatable conformance to reduce unnecessary SwiftUI re-renders

Major macOS performance and stability improvements, Outlook messaging support, smarter assistant context and memory, security hardening, and polished UI components.

• Significant macOS performance and stability improvements: fixes for chat scroll freezes, sidebar re-render cascades, main thread blocking during file I/O, and SwiftUI invalidation issues — resulting in a noticeably smoother and more responsive experience
• Outlook messaging support: Vellum can now connect to Microsoft Outlook as a messaging provider, joining the existing Slack integration and expanding where the assistant can be reached
• Smarter assistant context and memory: the assistant now seeds capability memories for all skills (including bundled ones) and CLI commands at startup, improves semantic search, and better manages context window estimates
• Security hardening across the assistant and gateway: removal of dangerouslySkipPermissions, stricter risk classifications for CLI subcommands and hooks directory mutations, validation of symlink targets before spawning, and tightened admin route authorization
• Polished UI components and design consistency: redesigned skill detail page, shared file browser, improved dropdown and navigation items, context window indicator, and a consistent page container layout

CLI signing key handling improvements and automatic key migration for smoother upgrades.

• Improved signing key handling in the CLI to ensure the gateway's on-disk key is correctly prioritized, preventing potential authentication issues
• Automatic migration of signing keys from the gateway disk when upgrading from versions prior to v0.5.14, ensuring a smooth upgrade experience without manual intervention

Thinking blocks in chat, overhauled memory and retrieval, /compact command, expanded model support, and collapsible sidebar sections.

• Thinking blocks are now visible in chat: the assistant's reasoning process is rendered inline as collapsible thinking blocks, giving users transparency into how responses are formed — thinking is now enabled by default
• Significantly improved memory and retrieval: batched extraction, HyDE query expansion, MMR diversity ranking, a serendipity layer for surfacing unexpected relevant memories, and a new top-N retrieval format
• New /compact slash command and context window indicator: manually trigger context compaction at any time, with a color-coded bar in the toolbar showing how full the context window is
• Expanded model support and OpenRouter catalog: DeepSeek, Qwen, Mistral, Meta, Moonshot, and Amazon models added; Anthropic's 1M context window beta and fast mode now supported; OpenAI reasoning effort wired through to the API
• Collapsible sidebar sections, channel conversations, and macOS polish: Scheduled and Background sidebar sections now collapsible with persisted state, channel-bound conversations displayed with read-only treatment