openwork/packages/docs/changelog.mdx

---
title: "Changelog"
---
<Update label="August 27th" tags={["🚀 New Features", "🐛 Bug Fixes", "🏗️ Refactoring"]}>

  ## [v0.18.39](https://github.com/different-ai/openwork/compare/v0.18.38...v0.18.39): Richer session artifacts and more resilient agent runs

  - Session files now live in the artifact rail instead of interrupting the chat transcript, with safer badge layout and responsive behavior on narrow screens.
  - Markdown can render Mermaid diagrams safely, and code blocks offer a word-wrap control for long lines.
  - Agent runs recover more reliably from idle admissions, queued follow-ups, event-stream restarts, Settings visits, and large workspace session histories.
  - OpenWork Cloud adds per-member managed-model credentials, paid browser access, desktop delivery for remote-session commands, and more reliable worker recovery.
  - Electron file transfers now work correctly across the remote bridge, and LiteLLM examples include synchronized model metadata.

  ## [v0.18.38](https://github.com/different-ai/openwork/compare/v0.18.37...v0.18.38): Split-view workflows and live sessions get more dependable

  - Added cross-workspace split view and transcript actions for resuming interrupted runs.
  - Live session status now survives navigation, workspace switches, and reattachment while long-running streams remain responsive.
  - Refined tool-call activity, thought grouping, artifact controls, and Library choices so active work is easier to follow and manage.
  - Cloud extension status now reflects real connectivity, remote-session capabilities reach cloud targets, and worker recovery avoids competing owners.
  - Added a pull-only Docker evaluation stack and strengthened enterprise licensing documentation and stewardship metadata.

</Update>

<Update label="August 26th" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.18.37](https://github.com/different-ai/openwork/compare/v0.18.36...v0.18.37): Managed dashboards arrive and everyday navigation gets faster

  - Organization-managed MCP App dashboards now render on desktop, with a personal grid and an add-from-Connect picker that refreshes automatically.
  - Code Mode and MCP Apps are enabled by default, and Dashboard visibility follows each deployment's availability controls.
  - Added an artifact code browser, branded connector tool calls, delegated-task shimmer, and smoother keyboard, Library, model, and chat controls.
  - Improved streaming and render performance, stabilized sidebar ordering and Settings state, and kept composer focus through refreshes.
  - Fixed Azure managed-provider credential selection and clarified Azure Foundry resource names for bring-your-own-key setup.

</Update>

<Update label="August 24th" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.18.36](https://github.com/different-ai/openwork/compare/v0.18.35...v0.18.36): Hosted MCP Apps and cloud sign-in become more reliable

  - Hosted MCP Apps now render through the credential-bound Den gateway, and Connect refreshes its MCP App catalog when cached inventory is incomplete.
  - Fixed Den callback routing, API-origin derivation, and cookie forwarding so hosted sign-in remains on the correct domain.
  - Workspace switches preserve live agent runs under load, while stale tool activity and scrolling no longer disrupt the active transcript.
  - Desktop update channel selection stays stable, Automation control-plane traffic is bounded, and standalone MCP requests stop retrying indefinitely.
  - Clarified the difference between local setup, managed OpenWork Cloud, OpenCode models, and OpenWork-managed models.

</Update>

<Update label="August 20th" tags={["🚀 New Features", "🐛 Bug Fixes", "🏗️ Refactoring"]}>

  ## [v0.18.35](https://github.com/different-ai/openwork/compare/v0.18.34...v0.18.35): Desktop respects Automation deployment controls

  - Desktop now shows Automation navigation and proposals and registers a runner only when the connected deployment explicitly enables Automations.
  - Older and self-hosted deployments that do not advertise Automation availability remain safely disabled.

  ## [v0.18.34](https://github.com/different-ai/openwork/compare/v0.18.33...v0.18.34): MCP Apps guide connection setup and Desktop automations recover cleanly

  - First-party MCP App cards now guide connection, plugin, and skill-created flows directly in chat, including useful recovery cards when a connection fails.
  - Desktop automations report outcomes, open their execution threads, and recover missed runs and credential failures more reliably.
  - Programs are now called Workflows, with obsolete selection tools and legacy MCP App surfaces removed.
  - MCP connections are more resilient to server recovery, protocol changes, OAuth refresh bursts, and stale credentials.
  - Added current product screenshots, enterprise desktop deployment guidance, and a deployment-level Automation control.

</Update>

<Update label="August 19th" tags={["🚀 New Features", "🐛 Bug Fixes", "🏗️ Refactoring"]}>

  ## [v0.18.33](https://github.com/different-ai/openwork/compare/v0.18.32...v0.18.33): Library setup gets clearer and background connections recover cleanly

  - The Library Add flow now starts with clear choices for skills, MCP connections, plugins, and repositories.
  - Desktop automations recover rejected credentials and slow down repeated reconnect attempts instead of getting stuck.
  - Cloud MCP health checks and GitHub token requests are bounded, preventing background connection work from running away.
  - Added a Google Cloud deployment prompt, stronger MCP OAuth validation, and more reliable release publishing.

  ## [v0.18.32](https://github.com/different-ai/openwork/compare/v0.18.31...v0.18.32): Workspace imports and SAML replay protection get safer

  - Workspace imports now reject archives that expand beyond safe file-count or size limits.
  - Fixed SAML replay protection so its reservation IDs remain compatible with stored identity records.
  - Clarified how administrators can validate a live Okta SCIM setup.

  ## [v0.18.31](https://github.com/different-ai/openwork/compare/v0.18.30...v0.18.31): Enterprise identity records stay valid

  - Linked SSO and SCIM accounts now always use valid identity IDs, preventing malformed enterprise account records.
  - Release validation is faster and extended-test failures produce clearer alerts.

</Update>

<Update label="August 18th" tags={["🚀 New Features", "🐛 Bug Fixes", "🏗️ Refactoring"]}>

  ## [v0.18.30](https://github.com/different-ai/openwork/compare/v0.18.29...v0.18.30): Queue follow-ups and simplify the session workspace

  - Follow-up messages now run sequentially, so queued work stays ordered instead of competing with the active turn.
  - The model picker is more compact and the session sidebar is denser, leaving more room for the conversation.
  - Improved slow-spec coverage, LiteLLM provider proof, and runtime failure handling make releases easier to validate.

  ## [v0.18.29](https://github.com/different-ai/openwork/compare/v0.18.28...v0.18.29): SSO setup respects verified domains

  - SSO configuration is now gated on domain verification, preventing an organization from enabling an identity provider before its domain is trusted.
  - Added the Okta SAML callback configuration and setup documentation.

  ## [v0.18.28](https://github.com/different-ai/openwork/compare/v0.18.27...v0.18.28): Connections move into the Library

  - Library and composer Connections now share one consistent experience for discovering and using organization capabilities.
  - Added the foundation for hosting native MCP Apps in the desktop's private host.
  - Improved Code Mode routing, public API proxying, and MCP synchronization reliability.

  ## [v0.18.27](https://github.com/different-ai/openwork/compare/v0.18.26...v0.18.27): Safer organization setup and signed Windows releases

  - Added the initial private-admin bootstrap flow for Den organizations.
  - Added public cloud deployment guides and improved Okta SSO/SCIM setup.
  - Windows builds are signed by default, and Sentry events now include the app version.

</Update>

<Update label="August 17th" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.18.26](https://github.com/different-ai/openwork/compare/v0.18.13...v0.18.26): Automations graduate, MCP Apps come alive, and sessions stay resilient

  - Automations are out of preview: propose recurring work from chat, choose a model and thinking level, review clearer receipts, restore earlier revisions, and run work on your desktop or in OpenWork Cloud.
  - MCP Apps now bring interactive tools directly into conversations. Install external apps through Connect, open agent-generated views inline, and save reusable Code Mode Programs for future runs and Automations.
  - Cloud setup is much smoother, with mobile and tablet support, automatic installer downloads, simpler organization sign-in, model-usage analytics, and a clearer dashboard organized around Work, Manage, Observability, and Team.
  - Connect is more dependable: organization models appear automatically and refresh without restarting, OAuth works with more providers, and the Library clearly explains connection failures. Marketplace is now called Collections throughout OpenWork.
  - Agent runs now survive provider updates, engine restarts, workspace switches, and intermittent cloud connection failures, alongside fixes for stuck uploads, startup failures, and interrupted sessions.

</Update>

<Update label="August 3rd" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.18.13](https://github.com/different-ai/openwork/compare/v0.18.12...v0.18.13): Extensions becomes the Library and skill sharing opens up

  - Extensions is now the Library — one place for everything your org can use, with tabs for what's ready, needs sign-in, or needs admin setup, on desktop and web.
  - Any organization member can now create plugins and cloud skills and share them straight from chat; access panels show who can use what, team by team.
  - Organizations can add multiple named Google Workspace connectors — each member signs in once per connector and agents pick the right account by name.
  - Chat now renders LaTeX math, shows immediate feedback while submitting, and adds number shortcuts to jump between visible sessions.
  - Recycled cloud sandboxes keep their chat history, and the artifact panel refreshes when the agent edits the open file.

</Update>

<Update label="July 30th" tags={["🐛 Bug Fixes"]}>

  ## [v0.18.12](https://github.com/different-ai/openwork/compare/v0.18.11...v0.18.12): Managed provider credentials reach the engine

  - Fixed managed cloud provider credentials so they reach the engine's auth API and org-approved models authenticate right after connecting.
  - Fixed the release pipeline to redeploy den-api when the sandbox snapshot pin changes.

</Update>

<Update label="July 29th" tags={["🐛 Bug Fixes", "🚀 New Features"]}>

  ## [v0.18.11](https://github.com/different-ai/openwork/compare/v0.18.10...v0.18.11): Live agent runs stop getting interrupted

  - Credential changes and background provider updates no longer tear down the agent event stream mid-run.
  - Composer skills, MCPs, and extensions load instantly from local data while cloud results land live.
  - Hardened Den organization lifecycles: invitations, re-invites, team cleanup, and legacy SSO/SCIM migration.
  - A malformed workspace list can no longer make the app unloadable.

</Update>

<Update label="July 29th" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.18.10](https://github.com/different-ai/openwork/compare/v0.18.9...v0.18.10): Org connections come to the desktop and cloud providers get dependable

  - Connect, reconnect, and disconnect organization connections directly from the desktop app.
  - Cloud LLM providers are now set up server-side and reach the engine globally, so org-approved models just work.
  - Cloud workspaces show status and version with a one-click update, and boot states replace stale error flashes.
  - Fixed organization invite lifecycles and redesigned the bring-your-own-key provider editor.

</Update>

<Update label="July 28th" tags={["🐛 Bug Fixes"]}>

  ## [v0.18.9](https://github.com/different-ai/openwork/compare/v0.18.8...v0.18.9): Linux installs repair themselves

  - Linux AppImages now integrate with the desktop, and the launcher repairs itself silently after updates — even on slow networks.
  - Den workers adopt an existing Daytona sandbox instead of getting stuck provisioning forever.

</Update>

<Update label="June 21st" tags={["🚀 New Features"]}>

  ## GLM 5.2, now in the API — with 2x usage

  - **GLM 5.2 in OpenWork Models** — GLM 5.2 is available through OpenWork Models with 2x usage, so your team can run real agent work on an open model at a fraction of the cost.
  - **Run your day from chat** — Tasks now organize into groups (In progress, Done, Requires attention) and you can move them by asking the chat instead of clicking.
  - **Split screen** — Two windows side by side. Keep a reference open on the left while you work on the right.
  - **Voice mode** — Control the OpenWork UI by voice. Talk through a task, navigate panels, and drive the agent without touching the keyboard.
  - **Advanced analytics on OpenWork Cloud** — Usage, activity, and team behavior in one view for teams running OpenWork at scale.

</Update>

<Update label="June 2nd" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.15.0](https://github.com/different-ai/openwork/compare/v0.14.1...v0.15.0): OpenWork learns session workflows and UI control

  - Added session management primitives for pinning, archiving, custom groups, group assignment, manual ordering, and drag-and-drop between groups.
  - Added UI control tools and capabilities knowledge so agents can navigate OpenWork itself, open settings, discover actions, and explain product capabilities from docs.
  - Improved artifact handling, provider picker promotion, environment-variable provider states, and sidebar group behavior.

</Update>

<Update label="June 1st" tags={["🚀 New Features", "🐛 Bug Fixes", "🏗️ Refactoring"]}>

  ## [v0.14.1](https://github.com/different-ai/openwork/compare/v0.13.12...v0.14.1): Cloud resources and Google Workspace move into the desktop flow

  - Added desktop cloud resource sync so org-managed providers, MCPs, and config can flow into the active desktop workspace.
  - Added Google Workspace OAuth setup and surfaced the Google Workspace extension in the app.
  - Improved provider-empty states, model picker behavior, message rendering, browser panel behavior, and desktop boot reliability.
  - Closed Cloud API trust-boundary issues around plugin-system grants and internal MCP principal impersonation.

</Update>

<Update label="May 21st" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.13.12](https://github.com/different-ai/openwork/compare/v0.12.8...v0.13.12): Cloud policies, marketplaces, extensions, and enterprise identity land

  - Added Cloud desktop policies for owners and admins to restrict desktop capabilities by org, member, or team.
  - Merged Cloud marketplace and extension management into the desktop Extensions experience, including built-in extension visibility and policy-controlled disable states.
  - Added org-scoped SCIM and SSO admin flows, member dashboard views, and Den server sandbox coverage.
  - Added Voice Mode, HandsFree and Computer Use extension surfaces, plus stronger permission-helper flows.
  - Imported Cloud MCPs into workspace config and improved environment variable settings.

</Update>

<Update label="April 29th" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.12.8](https://github.com/different-ai/openwork/compare/v0.11.212...v0.12.8): Electron release hardening and Cloud marketplace import

  - Expanded Electron releases across macOS, Linux, and Windows with migration controls and release recovery fixes.
  - Added Cloud plugin marketplace import and React cloud provider sync.
  - Improved composer behavior, skill creation, session resume stability, paste chips, inline errors, and settings noise.
  - Added user environment variable UI and per-server MCP enable/disable toggles.

</Update>

<Update label="April 20th" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.11.212](https://github.com/different-ai/openwork/compare/v0.11.210...v0.11.212): Den desktop controls tighten and Cloud providers stay in sync

  - Better org controls: Organization owners can now limit or block models, providers, and updates to specific releases.
  - Auto-sync cloud providers into the active org workspace. The app should be able to update, remove, and reconcile disconnects more reliably.
  - Improved admin flows in the cloud, with explicit names for LLM providers and a more robust active-org handling.

</Update>

<Update label="April 20th" tags={["🚀 New Features"]}>

  ## [v0.11.210](https://github.com/different-ai/openwork/compare/v0.11.207...v0.11.210): Den enterprise org controls expand and microsandbox preview lands

  - Added a microsandbox preview mode. Toggle in `Settings` > `Advanced` to enable it and test it out. That means no more docker as requirement to create fast, isolated workspaces.
  - Openwork Organization owners can now define allowed email domains. Active-Org-Aware Desktop sign-in, and rename their org. 
  - Better control for Org owners regarding who accepts invites and invite delivery failures.
  - Quality of life: Added Spanish and Catalan localization, a shortcut to access the docs in the app and made the landing page easier to read for agents.

</Update>

<Update label="April 13th" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.11.207](https://github.com/different-ai/openwork/compare/v0.11.206...v0.11.207): Windows downloads return and OpenWork speaks French

  - Restored free public Windows desktop downloads across the landing and download flows so Windows users can download installers again without a paid checkout path.
  - Added French localization for the OpenWork app so users can navigate core product surfaces in French.

</Update>

<Update label="April 7th" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.11.205](https://github.com/different-ai/openwork/compare/v0.11.202...v0.11.205): OpenWork Cloud launches for teams

  - OpenWork Cloud now has orgs, teams, shared skills and workers.
  - Added custom LLM providers so everyone in the company can use the same org-approved LLMs in Openwork.
  - As an org admin, you can control members, invitations, teams, and custom RBAC roles for your company.

  <table>
    <tr>
      <td>
        <img src="/images/cloud-dashboard-overview.png" alt="OpenWork Cloud dashboard overview" />
        <p><em>OpenWork Cloud</em></p>
      </td>
      <td>
        <img src="/images/cloud-skill-hub-access-and-skills.png" alt="Skill hub access and included skills in OpenWork Cloud" />
        <p><em>Shared skills</em></p>
      </td>
    </tr>
  </table>

</Update>

<Update label="April 4th" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.11.202](https://github.com/different-ai/openwork/compare/v0.11.200...v0.11.202): Translations support for several languages

  - Added Thai and Japanese in-app translations
  - Additional documentation, privacy, terms and conditions.

</Update>

<Update label="April 3rd" tags={["🚀 New Features"]}>

  ## [v0.11.200](https://github.com/different-ai/openwork/compare/v0.11.199...v0.11.200): Minor improvements around Cloud skills

  - Added an OpenWork Cloud skills catalog to the Skills page. 

</Update>

<Update label="April 2nd" tags={["🚀 New Features", "🐛 Bug Fixes", "🏗️ Refactoring"]}>

  ## [v0.11.199](https://github.com/different-ai/openwork/compare/v0.11.198...v0.11.199): Paywall for windows, skillsHub

  - Added a pricing page for Windows versions. 
  - Expanded Den with skill hubs, a new `den-api`, and a simpler org-invite signup flow.

</Update>

<Update label="March 31st" tags={["🐛 Bug Fixes"]}>

  ## [v0.11.198](https://github.com/different-ai/openwork/compare/v0.11.196...v0.11.198): Improved workspace export security 

  - Blocked sensitive workspace exports and showed warnings before sharing risky config or secrets.
  - Tightened import safety for workspace configuration and portable files.

</Update>

<Update label="March 30th" tags={["🚀 New Features", "🐛 Bug Fixes", "🏗️ Refactoring"]}>

  ## [v0.11.196](https://github.com/different-ai/openwork/compare/v0.11.194...v0.11.196): OpenWork resumes where you left off

  - Moved automations onto a dedicated page inside settings.
  - Got rid of the initial loading state on app open.

</Update>

<Update label="March 26th" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.11.194](https://github.com/different-ai/openwork/compare/v0.11.192...v0.11.194): Team template sharing and autocompaction

  - Auto compaction is done into the workspace config.
  - Keeps scheduled jobs live in-app, and adds a faster Den local-dev path.
  - Introduces Den organizations, member roles, invitations, custom roles, and org-scoped template APIs and screens.

</Update>

<Update label="March 25th" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.11.192](https://github.com/different-ai/openwork/compare/v0.11.190...v0.11.192): Better Workspace switching and detached workers

  - Switching a workspace no longer  flips the active worker.
  - Detached workers share credentials are now preserved across restarts

</Update>

<Update label="March 24th" tags={["🐛 Bug Fixes", "🚀 New Features"]}>

  ## [v0.11.190](https://github.com/different-ai/openwork/compare/v0.11.184...v0.11.190): More docs, improved safety around sharing.

  - More docs regarding onboarding and connection guides
  - Better restart and reconnect flows so it stays attached to the intended directory.
  - Local workers now stay localhost-only unles users opt into remote exposure

</Update>

<Update label="March 23rd" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.11.184](https://github.com/different-ai/openwork/compare/v0.11.181...v0.11.184): Docs reset, exa and local workspaces

  - Rebuilt the docs around a single CLI-first quickstart.
  - Enables Exa search from opencode settings.
  - More reliable first-runs and simplified remote connect modal.

</Update>

<Update label="March 22nd" tags={["🐛 Bug Fixes", "🏗️ Refactoring", "🚀 New Features"]}>

  ## [v0.11.181](https://github.com/different-ai/openwork/compare/v0.11.177...v0.11.181): Simplified den checkout and workspace sharing

  - Simplifies Den billing, dashboard and workspace creation flows.
  - Made model pickers model-aware with provider icons and per-model reasoning or behavior controls.

</Update>

<Update label="March 20th" tags={["🐛 Bug Fixes", "🚀 New Features", "🏗️ Refactoring"]}>

  ## [v0.11.177](https://github.com/different-ai/openwork/compare/v0.11.172...v0.11.177): Cloud worker heartbeats

  - Adds worker heartbeats for Cloud workers
  - Added Settings-based folder authorization and server-backed empty states

</Update>

<Update label="March 19th" tags={["🐛 Bug Fixes", "🏗️ Refactoring", "🚀 New Features"]}>

  ## [v0.11.172](https://github.com/different-ai/openwork/compare/v0.11.168...v0.11.172): Remote reconnects and cloud flows

  - Rebuilt Den webapp onboarding and billing.
  - Persisted worker share tokens and repeated deeplinks across restarts.
  - Added self-serve Cloud settings, OpenAI headless auth, and tray-on-close desktop behavior.

</Update>

<Update label="March 17th" tags={["🐛 Bug Fixes", "🚀 New Features"]}>

  ## [v0.11.168](https://github.com/different-ai/openwork/compare/v0.11.164...v0.11.168): Release recovery with repaired installers
  - Cloud Migration from render VMs to Daytona Sandbox workers
  - pnpm web:dev-local working reliably when starting from scratch in a new worktree 
  - Restored skill install flows and better cache clearing of disconnected provider credentials.

</Update>

<Update label="March 16th" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.11.164](https://github.com/different-ai/openwork/compare/v0.11.160...v0.11.164): Public skills and subagents

  - You can now add public repos as skill repository
  - Simplified docker testing pipeline
  - Minor sidebar bug fixes
  
</Update>

<Update label="March 15th" tags={["🐛 Bug Fixes", "🚀 New Features"]}>

  ## [v0.11.160](https://github.com/different-ai/openwork/compare/v0.11.159...v0.11.160): Bug fixes on den, telemetry and providers

  - Checkout handling for additional den workers
  - Landing page downloads points tot he right installer
  - Fixed release-pipeline diagnostics and in-app feedback email
  

</Update>

<Update label="March 14th" tags={["🐛 Bug Fixes", "🚀 New Features", "🏗️ Refactoring"]}>

  ## [v0.11.149](https://github.com/different-ai/openwork/compare/v0.11.146...v0.11.149): Better den onboarding flow and Oath

  - Simplified Den onboarding flow.
  - More polished feedback card and telemetry around bug reporting. 
  - Cloud skills can now be installed into existing workers.
  - ChatGPT Oath added to "New chat Session"

    <img src="/images/chatgpt-new-session-cta.png" alt="New session with Connect ChatGPT for free CTA" />

</Update>

<Update label="March 13th" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.11.146](https://github.com/different-ai/openwork/compare/v0.11.1444...v0.11.146): Den admin view and Aesthetic changes 

  - Den worker redeploys, better dekstop skill reload and adjustable sidebar width. 

</Update>

<Update label="March 12th" tags={["🐛 Bug Fixes", "🚀 New Features", "🏗️ Refactoring"]}>

  ## [v0.11.144](https://github.com/different-ai/openwork/compare/v0.11.140...v0.11.144): Workspace shell recovery and clearer docs entrypoints

  - Improved workspace shell recovery and inline error sessions
  - Cloud worker creation
  - Deprecated soul mode

</Update>

<Update label="March 11th" tags={["🚀 New features", "🐛 Bug Fixes"]}>

  ## [v0.11.140](https://github.com/different-ai/openwork/compare/v0.11.136...v0.11.140): Improved workers, sharing skills, GOAuth

  - Creating a new worker opens up an empty session instead of automations
  - Skill sharing improvements
  - Task list not sticking to the composer box
  - Google and GitHub

  <img src="/images/improved-skills-march11th.gif" alt="New worker opens on an empty session" />

</Update>

<Update label="March 10th" tags={["🚀 New Features", "🐛 Bug Fixes"]}>

  ## [v0.11.136](https://github.com/different-ai/openwork/compare/v0.11.135...v0.11.136): Improved model picker and MCP auth

  - Model picker now separates enabled and not-enabled providers, and clicking a disabled provider opens its settings.
  - MCP auth now waits for agents to stop or finish before continuing.

  <table>
    <tr>
      <td>
        <img src="/images/10thMarch-model-picker.gif" alt="Model picker grouped by enabled and not-enabled providers" />
        <p><em>Model picker</em></p>
      </td>
      <td>
        <img src="/images/10thMarch-better-mcp-auth.gif" alt="MCP settings with connected provider and improved auth handling" />
        <p><em>MCP auth</em></p>
      </td>
    </tr>
  </table>

</Update>