coder

Anyclaude — AI skill for Claude Code

AI community intermediate

GitHub Repo stars Claude Code with any LLM Multi-model support.

How to install Anyclaude

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

What Anyclaude does

[](https://www.npmjs.com/package/anyclaude)

Alternatives in AI

Kilocode — GitHub Repo stars Open Source AI coding assistant for planning, building, and fixing code Open source AI assis 17k ★
Context Engineering Intro — GitHub Repo stars Context engineering - the new way of AI coding assistants Context engineering guide 12.8k ★
Codecompanion.nvim — GitHub Repo stars AI-powered coding seamlessly in Neovim Neovim AI coding 6.3k ★

README

anyclaude

[](https://www.npmjs.com/package/anyclaude)

Use Claude Code with OpenAI, Google, xAI, and other providers.

Extremely simple setup - just a basic command wrapper
Uses the AI SDK for simple support of new providers
Works with Claude Code GitHub Actions
Optimized for OpenAI's gpt-5 series

Get Started

# Use your favorite package manager (bun, pnpm, and npm are supported)
$ pnpm install -g anyclaude

# anyclaude is a wrapper for the Claude CLI
# `openai/`, `google/`, `xai/`, and `anthropic/` are supported
$ anyclaude --model openai/gpt-5-mini

Switch models in the Claude UI with `/model openai/gpt-5-mini`.

GPT-5 Support

Use --reasoning-effort (alias: -e) to control OpenAI reasoning.effort. Allowed values: minimal, low, medium, high.

anyclaude --model openai/gpt-5-mini -e high

Use --service-tier (alias: -t) to control OpenAI service tier. Allowed values: flex, priority.

anyclaude --model openai/gpt-5-mini -t priority

Note these flags may be extended to other providers in the future.

FAQ

What providers are supported?

See [the providers](./src/main.ts#L17) for the implementation.

GOOGLE_API_KEY supports google/* models.
OPENAI_API_KEY supports openai/* models.
XAI_API_KEY supports xai/* models.

Set a custom OpenAI endpoint with `OPENAI_API_URL` to use OpenRouter

`ANTHROPIC_MODEL` and `ANTHROPIC_SMALL_MODEL` are supported with the `/` syntax.

How does this work?

Claude Code has added support for customizing the Anthropic endpoint with `ANTHROPIC_BASE_URL`.

anyclaude spawns a simple HTTP server that translates between Anthropic's format and the [AI SDK](https://github.com/vercel/ai) format, enabling support for any [AI SDK](https://github.com/vercel/ai) provider (e.g., Google, OpenAI, etc.)