posit-dev

AI Provider Bridge — DevOps skill for Claude Code

DevOps community

Platform-neutral provider infrastructure for LLM access.

How to install AI Provider Bridge

This entry records only its repository, not the path inside it, so there is no exact command to give. Open posit-dev/ai-provider-bridge and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What AI Provider Bridge does

Platform-neutral provider infrastructure for LLM access.

Alternatives in DevOps

Claude Code Router — Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the m 30.1k ★
Cloudflare Deploy — Deploy apps to Cloudflare using Workers, Pages, and platform services 14.6k ★
Supabase — Infrastructure Supabase database/auth integration 14k ★

README

ai-provider-bridge

Platform-neutral provider infrastructure for AI model access: registry, model clients, credential abstractions, and provider registration functions, with no dependency on VS Code or Node platform services.

Package Boundaries

These rules keep the dependency graph clean:

Root entrypoint must not import vscode -- only the /positron entrypoint may.
Must not import from consumer packages -- host applications depend on this package, not the reverse.

Entrypoints

Entrypoint	What it provides	Heavy deps?
`ai-provider-bridge`	`ProviderRegistry`, interfaces (`ModelClient`, `CredentialProvider`, `StepLogger`), `createCachedModelFetcher`, provider map, `LocalProviderManager`	No
`ai-provider-bridge/providers`	`register*Provider()` functions, client classes, helpers	Yes (AI SDK packages)
`ai-provider-bridge/positron`	`PositronCredentialProvider`, `VscodeLmClient`, `listVscodeLmModels()`, `fromAiMessages2()`, LM helpers	Yes (`vscode`)

Supported Providers

Provider	Client	Model Discovery
Anthropic	AnthropicClient	Cached via API
OpenAI	OpenAIClient	Cached via API
AWS Bedrock	BedrockClient	Cached via API
Google Gemini	GeminiClient	Cached via API
Google Vertex AI	GoogleVertexClient	Cached