Alishahryar1 / free-claude-code

2026-01-28 · Source: Github Trending: All languages · Field: Technology & Digital — Software Development & Engineering, Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure · Depth: Intermediate, long

Summary

Free Claude Code is a lightweight proxy that enables users to run Anthropic's Claude Code CLI and VSCode extension without requiring an Anthropic API key. It achieves this by routing Claude Code's API calls to alternative LLM providers such as NVIDIA NIM (offering 40 requests/minute free), OpenRouter, DeepSeek, LM Studio (for local execution), or llama.cpp. The proxy supports per-model mapping, allowing different Claude models (Opus, Sonnet, Haiku) to be routed to specific backend models and providers. Key features include local interception of five categories of trivial API calls to save quota, heuristic tool parsing, smart rate limiting, and support for Discord and Telegram bots for remote autonomous coding with session persistence and live progress. The system is extensible, allowing for easy integration of new providers or messaging platforms.

Key takeaway

For Machine Learning Engineers and developers seeking to utilize Claude Code without direct Anthropic API costs, this proxy offers a viable solution. You should configure your environment variables to point Claude Code to the proxy and select a backend provider like NVIDIA NIM for its free tier or LM Studio for local execution. This approach allows you to experiment and develop with Claude Code's capabilities while managing API expenses and leveraging diverse LLM models.

Key insights

A proxy enables free use of Claude Code by routing Anthropic API calls to alternative LLM providers.

Principles

• Transparent API proxying
• Quota optimization via local interception
• Flexible model routing

Method

The proxy translates Anthropic API requests to an OpenAI-compatible format for various LLM providers, intercepting trivial calls locally and converting thinking tokens and tool calls.

In practice

• Configure .env for preferred LLM provider
• Use `claude-pick` for interactive model selection
• Set up Discord/Telegram bots for remote coding

Topics

• Claude Code Proxy
• LLM Providers
• NVIDIA NIM
• OpenRouter
• LM Studio

Code references

• astral-sh/uv
• Alishahryar1/free-claude-code
• astral-sh/ruff
• Delgan/loguru
• anthropics/claude-code

Best for: Machine Learning Engineer, AI Engineer, Software Engineer, MLOps Engineer

Related on AIssential

• Pairing Claude Code with Local Models — Local models can replace cloud APIs for Claude Code, offering cost savings and no rate limits.
• Connecting Claude Clients with Azure API Management and Claude Models in Microsoft Foundry — An Azure API Management gateway provides secure, metered access to Anthropic Claude models in Microsoft Foundry.
• Claude Code + OpenRouter = Free UNLIMITED AI Coding (No Local Setup) — Open Router enables free, cloud-powered AI model inference within Claude Code, overcoming local hardware limitations.
• NVIDIA's New Free AI - A Gift To Humanity — NVIDIA's NeMoTron 3 Ultra is a fast, open-licensed, text-only 550B parameter model excelling in agentic tasks but not complex coding.
• Free Claude Max for (large project) open source maintainers — Anthropic offers free Claude Max 20x access to qualifying open source project maintainers for six months.
• Claude Code + Ollama = FULLY FREE AI Coding FOREVER! (Tutorial) — Integrate Claude Code with Ollama to run open-source LLMs locally, leveraging agentic capabilities for free.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Github Trending: All languages.