claude-code-forge: Access Any AI Model Through Claude's Interface
This repository profile is provided by osrepos.com, an open source repository discovery platform.

Summary
claude-code-forge is a utility that enables users to access a wide array of AI models through the Claude Code interface. By configuring Claude Code to use TensorBlock Forge as its API provider, developers can leverage models like Qwen Coder and Gemini, expanding beyond Claude's default offerings. This repository provides simple setup scripts to integrate TensorBlock Forge seamlessly.
Repository Information
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
claude-code-forge is a straightforward setup utility designed to integrate TensorBlock Forge with Claude Code. This powerful combination allows you to access and utilize a diverse range of AI models directly through Claude's familiar interface, moving beyond its default offerings.
This repository provides essential startup scripts that configure Claude Code to use TensorBlock Forge as the API provider. This means you can tap into models like Qwen Coder, Gemini, and many others, enhancing your development capabilities within the Claude Code environment.
Installation
To get started with claude-code-forge, follow these steps:
Prerequisites
- Claude Code: Ensure you have Claude Code installed on your system.
- TensorBlock Forge API Key: Sign up at forge.tensorblock.co and obtain your API key.
Setup Steps
- Get your API key:
- Visit TensorBlock Forge.
- Sign up for an account.
- Add your preferred model provider API keys.
- Generate a Forge key from your dashboard.
- Configure the script:
Edit the appropriate script for your platform and replace
YOUR_TENSORBLOCK_FORGE_API_KEYwith your actual API key.For Linux/Mac (
start_claude_code.sh):export ANTHROPIC_AUTH_TOKEN=your_actual_forge_key_hereFor Windows (
start_claude_code.bat):set ANTHROPIC_AUTH_TOKEN=your_actual_forge_key_here - Make the script executable (Linux/Mac only):
chmod +x start_claude_code.sh
Examples
Once configured, using claude-code-forge is simple:
Linux/Mac
./start_claude_code.sh
Windows
start_claude_code.bat
Default Configuration:
The provided scripts are pre-configured with:
- Primary Model:
Fireworks/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct, a powerful coding model. - Fast Model:
Gemini/models/gemini-2.5-flash, for quick responses.
You can easily modify these models within the script files to use any model available on TensorBlock Forge.
Why Use It?
claude-code-forge offers several compelling advantages:
- Expanded Model Access: Utilize a wide variety of AI models beyond Claude's default offerings, including specialized coding models and faster response models.
- Unified Interface: Access diverse models through the familiar and intuitive Claude Code interface, streamlining your workflow.
- Flexibility: Easily switch between different models by modifying the configuration scripts.
- Self-Hosting Option: For enhanced privacy and control, you can self-host TensorBlock Forge, managing your API keys and infrastructure directly. Visit the TensorBlock Forge repository for more details.
Links
- GitHub Repository: TensorBlock/claude-code-forge
- TensorBlock Forge: forge.tensorblock.co
- TensorBlock Model Catalog: tensorblock.co/api-docs/model-ids
- TensorBlock Forge Self-Hosting: TensorBlock/forge
Related repositories
Similar repositories that may be relevant next.

mcp-gateway: Unifying AI Tool Access with Reduced Context Overhead
August 15, 2026
mcp-gateway is a powerful Rust binary designed to streamline AI agent interaction with diverse tools. It consolidates unlimited MCP servers and REST APIs behind a single, compact endpoint, drastically reducing context token overhead and enabling efficient tool access.

Jan: An Open-Source, Offline ChatGPT Alternative for Your Desktop
August 14, 2026
Jan is a powerful open-source desktop application that provides a 100% offline alternative to ChatGPT. It allows users to download and run various large language models locally, ensuring complete control and privacy over their AI interactions. With support for multiple platforms, Jan offers a robust solution for personal and private AI use.

TurboLLM: Run Local LLMs with Auto-Tuning, Any Engine, and a Polished UI
August 13, 2026
TurboLLM is a powerful, lightweight solution for running local LLM engines, offering auto-tuning for your GPU and a polished web UI. It supports any llama-server compatible binary, including community forks, and provides both OpenAI and Anthropic-compatible APIs. This offline-first tool allows users to maximize performance and flexibility with their local language models.
OpenSandbox: A Secure and Extensible Sandbox Runtime for AI Agents
August 12, 2026
OpenSandbox is a powerful, general-purpose sandbox platform designed for AI applications. It provides secure, fast, and extensible runtime environments, supporting multi-language SDKs and Docker/Kubernetes deployments. This project is ideal for developing and evaluating AI agents in isolated, controlled settings.
Source repository
Open the original repository on GitHub.
20 counted GitHub visits