LoginSign Up
← Back to all sparks
C

Cherry Studio

AI-ASSISTANTS
Velocity5.0

Desktop AI client supporting multiple LLM providers and knowledge bases.

www.cherry-ai.com ↗

Cherry Studio is on a v2.2.0 release branch, fed by automated backports.

desktop-ai-clientrelease-processbackportsllm-providers
◆Current state
Cherry Studio ran a v2.0.0 release train of betas and candidates in late July, then shipped patch releases such as v2.0.6. The feed now shows a release/v2.2.0 branch receiving fixes from main through automated, DCO-signed backport pull requests that must pass CI before merging. The backport itself carries no user-facing detail.
◆Where it's heading
The project has moved from the v2 rewrite to versioned release branches with a formal backport process. That points to a more structured cadence, though the feed shows little of what v2.1 or v2.2 add for users.
◆Prediction
A v2.2.0 release is the likely next entry; what it contains is not visible from the backport notes.

◆Recent moves

  1. 4d ago

    Backport of fix #24037 to the v2.2.0 release branch

    An automated pull request copies one fix from main onto release/v2.2.0, with the notes describing process rather than the fix. It shows the project now maintains release branches, but nothing user-visible.

    View source ↗
  2. 1mo ago

    mlx-node package tag: Azure URL preview respects apiVersion

    A package tag rather than an app release, and its one line of notes is a fix making the Azure URL preview honor a user-set apiVersion. It says nothing about the post-v2 direction.

    View source ↗
  3. 2mo ago

    Files page keeps the upload button in every category

    A single fix: the Files page hid the upload button outside the All files view, so uploading from an Image or Document category meant navigating back first. It is the first patch after the v2 train and reads like the start of routine maintenance rather than a continuation of the rewrite.

    View source ↗
  4. 3mo ago

    rc.5: Gemma 4 thinking in Ollama, anchor rail navigation

    The last candidate before v2 carried real additions among the fixes - Gemma 4 thinking mode through Ollama, a minimal tick-rail for message anchor navigation, save-as actions in image preview - alongside streamed code-block and file-processing repairs. It is the point where the train stopped being purely defensive.

    View source ↗
  5. 3mo ago

    rc.4: Radeon Cloud provider and configurable endpoints

    Adds a Radeon Cloud provider integration and lets users change a provider's default endpoint, plus unified file and artifact preview routing and a converged semantic color contract. Provider breadth is the one axis Cherry Studio kept extending while the rest of the train handled migration.

    View source ↗
  6. 3mo ago

    rc.3: knowledge, export, and accessibility fixes

    Accessibility labels on page-zoom controls, an Obsidian export dialog that stays open on failure, readable names for saved knowledge messages, and a shared resource-group creation dialog. Cleanup work with nothing a user would call a new capability.

    View source ↗