Skip to content

feat: add OrcaRouter as an OpenAI-compatible provider preset - #27

Open
nissrin2020ali-ux wants to merge 1 commit into
yejiming:mainfrom
nissrin2020ali-ux:feat/add-orcarouter-provider
Open

feat: add OrcaRouter as an OpenAI-compatible provider preset#27
nissrin2020ali-ux wants to merge 1 commit into
yejiming:mainfrom
nissrin2020ali-ux:feat/add-orcarouter-provider

Conversation

@nissrin2020ali-ux

Copy link
Copy Markdown

MuseAI's README describes it as "a local AI interaction world that keeps your characters, settings, memories, and relationships in one place," built for people who "prefer keeping stories, settings, and sessions on their own computer while using their own API key." Users already bring their own key and plug into OpenAI-compatible providers — DeepSeek, Kimi, Zhipu, and proxy services — by entering a base URL, key, and model name in Settings.

For a MuseAI user who wants a single provider namespace across many models without juggling several upstream keys, the settings page already ships presets such as OpenRouter. This PR adds OrcaRouter as a first-class preset next to it, so those users can reach the gateway with one click instead of treating it as an anonymous Custom base URL.

OrcaRouter is an OpenAI-compatible AI gateway built for both models and agents. Like OpenRouter, it exposes a provider/model namespace across many models — but it also combines adaptive routing, automatic failover, zero-markup inference, observability, guardrails, and agent-tool governance behind the same endpoint. Adding orcarouter as a first-class provider means this project's users can use that stack directly, without treating OrcaRouter as an anonymous custom base URL.

It also runs gateway-level, zero-trust security for AI agents on the same endpoint — screening every prompt/response and governing every tool call on a default-deny basis, with no application code changes.

What changed

  • Added one entry to MODEL_PROVIDER_PRESETS in src/pages/Settings.tsx, mirroring the existing OpenRouter preset:
    • Provider: OrcaRouter
    • Base URL: https://api.orcarouter.ai/v1
    • Interface: OpenAI-compatible

Because OrcaRouter speaks the OpenAI-compatible protocol, the preset flows through MuseAI's existing OpenAI-compatible request path (test_llm_connection and the chat/agent sessions) — no backend changes are required.

Verification

  • npm run test — 285 tests pass
  • npm run build (tsc + vite build) — succeeds
  • Live connection test against https://api.orcarouter.ai/v1/chat/completions using the same streaming SSE format MuseAI's connection test reads — HTTP 200

Discord: discord.gg/YEubt8enRA · X: https://x.com/OrcaRouter

I'm an engineer on the OrcaRouter team.

Add OrcaRouter (https://api.orcarouter.ai/v1) to the provider presets in
the settings page, mirroring the existing OpenRouter entry. OrcaRouter is
an OpenAI-compatible gateway, so it works with the existing
OpenAI-compatible interface without any backend changes.

Co-Authored-By: Claude <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant