Add Provider

Add-provider is a guided workflow for wiring a new LLM provider into the DeepChat codebase, and it's strict about it. Before touching any files it wants a provider ID, base URL, auth type, model metadata source, and a test model, then it sorts the request into one of three paths: an OpenAI-compatible API, an existing native transport like Anthropic or Ollama, or a special adapter when the API genuinely differs. The guardrails are the interesting part. It refuses to add runtime manifests, auto-install SDKs, run provider logic in the renderer, or create a custom adapter when a known transport would do. If you're adding a provider to DeepChat, this keeps you from over-engineering it. The checklist at the end is handy for code review too.

GitHub stars: 6.2K
last updated: Aug 3, 2026

View on GitHub

Install

$ npx -y skills add ThinkInAIXYZ/deepchat --skill add-provider --agent claude-code

Installs into .claude/skills of the current project.

Files

Add Provider

Goal

Generate DeepChat provider integration changes against the current provider architecture. Keep provider display data in PublicProviderConf, map runtime behavior to known transports, and use a special provider implementation only when the API behavior requires one.

Required Inputs

Collect or derive these before editing source:

Provider ID in kebab case.
Display name.
API type or known transport family.
Default base URL.
Auth type: API key, no auth, OAuth, profile credentials, or provider-specific credential.
Model metadata source: built-in config, provider-db, config-db, live model fetch, or custom only.
Test model ID and check strategy.
Official website, API key URL, docs URL, model list URL.
Request quirks: headers, endpoint suffixes, route rewrites, streaming shape, tool-call support, reasoning support, image/audio/embedding endpoints, or proxy requirements.