Product updates · Updated Oct 11, 2026 · 5 min read

Product changelog

Product changes and released capability updates for Lerix.

October 11, 2026 update

A refreshed look and more reliable everyday chat

  • A refreshed Lerix identity. New app icons, a rounded companion mark, and updated light and dark themes across the chat workspace.
  • More reliable composing. Improved sizing and controls in the Mac app's Quick Composer.
  • Chat and attachment reliability. Improved handling of streamed responses and file and image attachments.
  • Security improvements.

October 3, 2026 update

Optional Agent memory and more reliable chat sync

  • Memory across separate Agent chats. Optional Agent memory lets a saved Agent recall information from its other chats. Enable it for each Agent, choose whether Agent chats use it by default, and control it with the Memory switch in each chat.
  • Memory is a paid feature in testing with daily limits. It uses a third-party service and is not end-to-end encrypted. Read the memory privacy, limits, and deletion details before enabling it.
  • More stable Agent chats. Improved reliability when sending messages with saved Agents.
  • More reliable favorites sync. Improved encrypted syncing of favorite model configs and Agents across devices.

September 30, 2026 update

Security maintenance

  • Security improvements.
  • Security improvements in build dependencies.

September 29, 2026 update

Security maintenance

  • Security improvements in app dependencies.

September 28, 2026 update

More polished iPhone voice and analytics reliability

  • Better voice on iPhone. Voice uses the phone speaker when no headset is connected, with smoother animation and clearer connection feedback. Using voice.
  • Analytics reliability improvements across the web app, docs, and Mac app.

September 26, 2026 voice update

Simpler voice setup and lighter mobile animation

  • Connect once, start talking. A ready ChatGPT connection enables voice on your Mac and through Relay automatically. Your iPhone shows microphone controls when it detects the connection. You can turn either option off in Voice settings. Voice setup.
  • Lighter iPhone voice animation. Voice movement now uses native animation without repeatedly rebuilding the controls. Little wave, Soft dash and Crescent keep their audio reactions and reduced-motion support. Using voice.

September 26, 2026 update

Experimental ChatGPT voice and appearance choices

  • Voice in your chats. Eligible paid accounts can connect ChatGPT in Settings > Voice, talk in a normal chat, and continue with text. Choose Little wave, Soft dash or Crescent for the voice animation. Set up voice.
  • Voice through your Mac. Enable Use voice on other devices to use the Mac's voice connection from the mobile web app or an updated iOS build. Keep the Mac open; ChatGPT subscription limits and runtime availability apply.
  • Your preferred appearance. Follow the system appearance or choose Light, Dark or Papyrus in Settings. Landing-page previews and Settings layouts have also been refined.
  • Security improvements.

September 25, 2026 update

Current Codex models, reliable model selections, and security maintenance

  • Codex model discovery. The Mac app discovers supported models for your signed-in Codex account, including GPT-6 Astra, Sol, and Luna when available. Learn about Codex access.
  • Your model choices stay yours. Disabled connection models remain hidden when settings sync, and Codex reasoning controls follow the selected model. Edit your model list.
  • Security and reliability. Updated the desktop runtime and dependencies, strengthened web request handling, and improved account restoration and mobile interactions.

September 6, 2026 design update

A lighter workspace with refreshed typography and controls

  • The web app has a refreshed light appearance across chats, navigation, the model picker, and Settings, with new typography and green accents.
  • Conversation and Settings scrollbars now match their surrounding surfaces, including narrow mobile layouts.

September 6, 2026 update

GPT-6 Astra, clearer product demos, and composer improvements

August 31, 2026 update

Adaptive model routing, clearer Settings, faster chat, and Mac reliability

  • Lerix Auto can now choose among eligible local Ollama, connected API-key, and Codex or Relay response paths for each prompt, with Adaptive, Faster, and Favor quality controls.
  • Connections settings now use a compact searchable model picker, while Settings has a clearer desktop layout and phone-friendly section navigation.
  • Quick Composer hands prompts into normal Mac app response windows more reliably and preserves the signed-in account experience across those windows.
  • Long streaming responses render more smoothly, and noncritical startup work is deferred so the chat surface becomes ready sooner.
  • Lerix now uses its refreshed layered mark and app icon across the web, Mac, and mobile app surfaces.
  • Security and reliability improvements.

August 26, 2026 update

  • Security and reliability improvements.

August 25, 2026 update

  • Security and reliability improvements.

August 23, 2026 update

  • Security and reliability improvements.

August 12, 2026 update

New models, local AI, safer account access, usage tracking, and Mac reliability

July 3, 2026 update

Mobile docs comparison polish and web analytics reliability

  • The plan comparison table now stays contained on phone-width docs pages, so readers can scroll the comparison without horizontally panning the whole page.
  • Web analytics now measures aggregate visit quality, visit duration, and Core Web Vitals more accurately while preserving Lerix's privacy-safe analytics boundaries.

June 21, 2026 update

Clearer landing page, mobile visitor flow, and alpha labeling

  • The public first screen now shows a more product-like Lerix workflow with clearer model access, provider compatibility, and pricing cues.
  • Multi-model responses, Saved Agents, Codex auth and Relay, and chat storage choices are now represented with focused Lerix UI previews.
  • The mobile visitor experience now has a tighter account-first CTA flow, a compact menu, mobile-sized product previews, and visible alpha status in the top bar.

June 16, 2026 update

Mac status menu, Relay controls, update prompts, and favorite comparisons

  • Quick Composer is now available from the Mac status menu with its keyboard shortcut shown in the menu.
  • Codex Relay can now be turned on or off from the Mac status menu, with compact On/Off status while the desktop app is running.
  • Mac app windows and the status menu now behave more consistently when the app stays open in the background or fully quits.
  • Mac app update prompts now include restart actions in the status menu, including restart-after-download when an update is still downloading.
  • Saved Agent favorites can now be compared with favorite model configs while keeping Agent personality and file context attached to the Agent response only.
  • Multi-model responses now keep favorite comparison targets aligned with the visible composer state after selection and send.

June 15, 2026 update

OpenRouter, mobile web polish, and Mac app reliability

June 14, 2026 update

Account, billing, relay, comparison, support versioning, and trust updates

  • Account setup, sign-in, and billing flows now resume more consistently after refreshes, email confirmation, checkout, and account-session checks.
  • Encrypted account data access now gives clearer recovery-key and workspace-continuity handling during signup and sign-in.
  • Codex auth and Relay now handle same-account desktop and relay access more consistently where supported.
  • Multi-model responses now keep the selected comparison models visible in the composer after a send.
  • Support version details now reflect the tagged production release and build identity more consistently across Lerix surfaces.
  • Public docs now reflect current account, plan, storage, Codex, and model setup behavior with date-labeled product updates.
  • Security improvements.

June 4, 2026 update

Saved Agents, comparison controls, and Codex Relay polish

  • Pro accounts can now save Agents with a name, exact model config, personality prompt, and optional files from the model menu.
  • Agents can be starred as favorites, so favorite rows and shortcut switching preserve the Agent profile together with its model and access path.
  • Multi-model responses now show clearer per-response config details and keep branch selection stable when responses are included or dropped from the next round.
  • Codex auth and Relay now use clearer source labels and include reliability improvements.
  • Security improvements.

May 30, 2026 update

Direct streaming and cleaner response spacing

  • Streaming responses now render new text as it arrives from ChatGPT, Claude, Gemini, Grok, or a desktop relay instead of adding extra app-side pacing.
  • Prose and story responses now keep readable paragraph spacing when an AI service sends paragraph breaks as single newlines.

May 29, 2026 streaming update

Smoother streaming across model providers

  • Streaming responses now use a shared provider-agnostic scheduler that smooths bursty model deltas for ChatGPT, Claude, Gemini, Grok, and desktop relay responses.
  • When a provider finishes sending a response, Lerix now renders any remaining buffered text immediately instead of continuing at the active streaming pace.

May 29, 2026 stability update

Streaming stability across model responses

  • Streaming responses now stay stable while Lerix saves and syncs chat updates, preventing partial assistant text from being replaced during an in-progress response.

May 29, 2026 model update

Claude Opus 4.8, favorite-backed new chats, and model connection maintenance

May 27, 2026 update

Quick Composer, model favorites, new-chat defaults, and security improvements

May 26, 2026 update

Multi-model responses, support, model controls, and mobile web polish

  • The model menu now groups selectable models by AI service and keeps API-key or session access selection inside the active service.
  • ChatGPT model selection now keeps ChatGPT API-key access and Codex auth together under ChatGPT when both are available.
  • The composer now includes model search and favorite model configs, so the current model, access path, Intelligence, and Speed can become the starting setup for future new chats.
  • Pro accounts can compare multiple model responses from connected model configurations, review them side by side, and choose the response branch to continue.
  • Streaming responses can now be stopped from the composer, keeping the partial assistant message in the chat.
  • The latest user message can now be edited and resent. Edit mode keeps the original response visible until the resend starts and includes a cancel action.
  • Google API keys can now discover supported newly available Gemini text models automatically.
  • The model menu now exposes more AI-service-backed controls, including OpenAI response verbosity, Claude effort, Gemini thinking, and Grok reasoning where supported.
  • The mobile web app now uses larger chat controls, phone-native model and action sheets, and compact Settings tabs for easier use on phones.
  • Support and feedback now uses a signed-in form, with the reply email and account context attached from the Lerix account instead of an editable email field.

May 19, 2026 baseline

Initial release baseline

Initial released Lerix capabilities: