Appreciation
VibeAround's premise — keep Claude Code, Codex CLI, Gemini CLI, Pi, and the rest side by side, and let profiles route them to third-party APIs "without hand-editing each agent's config files back and forth" — is a problem anyone juggling several coding agents recognizes. The bridge is the part I appreciate most: saving a provider key, base URL, and model aliases once, then letting the Anthropic Messages, OpenAI Chat Completions, and Gemini Generate Content dialects translate underneath, is exactly the abstraction the third-party provider story needs.
That abstraction is also why the provider list is worth growing. Your catalog already ships presets for OpenRouter, DeepSeek, DashScope, and others, which tells me profile users want one credential that reaches many models.
Proposal
Add OrcaRouter as an optional built-in provider profile, alongside the existing presets. This is purely additive: it would not replace, reorder, or change any provider, endpoint group, or profile behavior that exists today.
Why it maps onto the existing abstraction
OrcaRouter exposes an OpenAI-compatible API and uses standard API-key authentication, so it fits the profile model directly — a base URL, a key, and a model list. The natural integration point is a new catalog entry next to the current presets, with the existing custom-endpoint profile remaining the fallback path. Because the bridge already speaks OpenAI Chat Completions / Responses, Anthropic Messages, and Gemini Generate Content, no new API shapes should be required. Nothing here is implemented or tested yet — this is a proposal.
Capabilities that seem genuinely relevant to VibeAround users:
- Multiple chat, reasoning, image, and video models through one endpoint — matches the "one subscription across all your agents" workflow your model-profiles guide describes.
- Automatic model routing and provider failover — long agent sessions are less likely to break when one upstream degrades mid-conversation.
- Usage tracking and budgets — your comparison table lists usage and cost tracking as roadmap; a routed endpoint reports usage centrally instead of per provider.
Ecosystem and disclosure
OrcaRouter is already used across open-source projects such as RAGFlow, Dify, goose, and promptfoo. OrcaRouter also runs an optional open-source partner program: approved OSS projects can receive a 5% revenue share from OrcaRouter usage attributed to their integration. Participation is not a prerequisite for this integration — it is a separate, opt-in arrangement, and I am glad to follow whatever disclosure or governance rules this repository sets.
More detail: https://www.orcarouter.ai/built-with
If an OrcaRouter preset fits your roadmap, I would welcome your thoughts on naming and placement, and I am happy to prepare an implementation PR once you are comfortable with the direction. I'm an engineer on the OrcaRouter team.
Appreciation
VibeAround's premise — keep Claude Code, Codex CLI, Gemini CLI, Pi, and the rest side by side, and let profiles route them to third-party APIs "without hand-editing each agent's config files back and forth" — is a problem anyone juggling several coding agents recognizes. The bridge is the part I appreciate most: saving a provider key, base URL, and model aliases once, then letting the Anthropic Messages, OpenAI Chat Completions, and Gemini Generate Content dialects translate underneath, is exactly the abstraction the third-party provider story needs.
That abstraction is also why the provider list is worth growing. Your catalog already ships presets for OpenRouter, DeepSeek, DashScope, and others, which tells me profile users want one credential that reaches many models.
Proposal
Add OrcaRouter as an optional built-in provider profile, alongside the existing presets. This is purely additive: it would not replace, reorder, or change any provider, endpoint group, or profile behavior that exists today.
Why it maps onto the existing abstraction
OrcaRouter exposes an OpenAI-compatible API and uses standard API-key authentication, so it fits the profile model directly — a base URL, a key, and a model list. The natural integration point is a new catalog entry next to the current presets, with the existing custom-endpoint profile remaining the fallback path. Because the bridge already speaks OpenAI Chat Completions / Responses, Anthropic Messages, and Gemini Generate Content, no new API shapes should be required. Nothing here is implemented or tested yet — this is a proposal.
Capabilities that seem genuinely relevant to VibeAround users:
Ecosystem and disclosure
OrcaRouter is already used across open-source projects such as RAGFlow, Dify, goose, and promptfoo. OrcaRouter also runs an optional open-source partner program: approved OSS projects can receive a 5% revenue share from OrcaRouter usage attributed to their integration. Participation is not a prerequisite for this integration — it is a separate, opt-in arrangement, and I am glad to follow whatever disclosure or governance rules this repository sets.
More detail: https://www.orcarouter.ai/built-with
If an OrcaRouter preset fits your roadmap, I would welcome your thoughts on naming and placement, and I am happy to prepare an implementation PR once you are comfortable with the direction. I'm an engineer on the OrcaRouter team.