⚖MikeWatch Forks of the Mike legal-AI codebase, distilled for legal-tech readers
Home · ranade-oss/ROSS-RanadeOSS · this thread

ranade-oss turns ROSS into a multi-model legal AI workspace

The fork is opening its chat system to more AI providers, giving users more choice over the model behind the work.

integrationchat-ui

ranade-oss has expanded a previously narrow AI setup into a broader provider layer, covering Claude, Gemini, OpenAI, Grok and Kimi. The practical change is less about novelty than optionality: teams can match the model to the job, availability or their existing provider relationship.

  • Grok access: users can connect xAI's model service with their own key.
  • Kimi access: users can connect Moonshot's model service with their own key.
  • Shared provider handling: the new services are brought into a common setup rather than treated as one-off additions.
  • Provider controls: the interface and model selection catalogue have been expanded to expose those choices.

The new key-storage path includes encryption at rest, but it merits a closer security review before being treated as fully vetted.

So what Legal teams testing different AI models, or product teams avoiding dependence on one vendor, should take a closer look.

View this fork on GitHub →

Spotted something wrong? Or know the PR text has fresher detail than the writeup above?

Commits in this thread

1 commit from ranade-oss/ROSS-RanadeOSS, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date
2a11a3f2 Add Claude, Gemini, Grok, Kimi, and OpenAI providers ranade-oss 2026-07-28 ↗ GitHub
commit body 
* Enable hosted model providers

* Enable hosted model providers in rehearsal

* Add OpenAI-compatible provider adapter

* Add xAI and Moonshot provider types

* Route Grok and Kimi through compatible adapters

* Register Grok and Kimi models

* Store xAI and Moonshot API keys

* Add hosted defaults for Grok and Kimi

* Discover Grok and Kimi model availability

* Approve xAI and Moonshot runtime providers

* Allow xAI and Moonshot user API keys

* Approve hosted Grok and Kimi providers

* Approve rehearsal Grok and Kimi providers

* Show Grok and Kimi models

* Support Grok and Kimi availability

* Group Grok and Kimi catalog models

* Add Grok and Kimi key controls

* Expose Grok and Kimi API keys

* Automate PR release manifest refresh

* Refresh release manifest from exact branch bytes

* Restore read-only Baseline verification

* Make Baseline verify regenerated manifest bytes

* Update runtime provider test for Grok and Kimi

* Fix provider key header typing

* Fix provider typing in model catalog

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Capture this thread into my fork

Download a single Markdown prompt that tells Claude how to port every commit above into your working tree — adapting paths and structure to match your repo. Run it via claude -p < capture-thread-897.md from inside the repo you want the changes in.

⬇ Download capture-thread-897.md