Alishahryar1/free-claude-code

Use Claude Code, Codex, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly)

What it solves

Free Claude Code (FCC) provides a unified interface to access a vast array of AI coding agents and LLM providers, allowing users to leverage free, paid, or local models without being locked into a single provider. It solves the problem of provider outages and high token costs by implementing automatic fallbacks and token optimization filters.

How it works

FCC acts as a proxy and management layer that connects various coding agents (such as Claude Code, Aider, and Cline) to over 60 different model providers. It includes an Admin UI for configuring API keys and model selection, and it offers native browser-based code sessions. To reduce costs, it integrates optional filters like RTK and Headroom to compress tool results and filter common command output.

Who it’s for

Developers who want to use multiple AI coding agents and LLM providers interchangeably, those seeking to minimize token usage and costs, and users who prefer to run local models (via Ollama, LM Studio, or llama.cpp) alongside cloud-based ones.

Highlights

  • Extensive Provider Support: Access to 61 ToS-friendly providers and over 1.3 billion free tokens monthly.
  • Agent Interoperability: Compatible with 11 different coding agents including Claude Code, Codex, and Aider.
  • Automatic Fallbacks: Automatically switches to the next configured model if a provider fails, preventing session restarts.
  • Token Optimization: Reduces token usage by up to 90% through command output filtering and result compression.
  • Multi-Platform Support: Works across terminal, desktop, IDEs (VS Code, JetBrains), and messaging apps (Discord, Telegram).
  • Voice Integration: Supports voice-to-code using local Whisper or NVIDIA NIM transcription.

Related

  • Project
    hkqr/my-free-code

    A multi-provider gateway that allows coding agents to use various LLM providers and local models via a unified proxy with automatic fallback routing.

  • Project
    kaitranntt/ccs

    A multi-provider profile and runtime manager that allows users to switch between different AI providers, local models, and account contexts via a unified CLI and dashboard.

  • Project
    SakuraByteCore/codexmate

    A local-first control plane and dashboard for managing multiple local AI coding agents, providing unified session browsing, provider configuration, and task orchestration.

  • Project
    caidaoli/ccLoad

    ccLoad is a self‑hosted Go gateway that unifies access to multiple LLM providers (Claude, OpenAI, Gemini, Codex, etc.). It lets you manage many API keys or subscription accounts as *channels*, presents a single endpoint and token to client tools, automatically fails over between channels, converts between different request protocols, and records usage and cost. Install via Docker, Homebrew, or a binary, configure channels through a web console, and point your Claude Code, Codex CLI, or any OpenAI‑compatible SDK at the gateway.

  • Project
    raine/claude-code-proxy

    A local proxy that lets Claude Code use multiple LLM providers (Codex, Kimi, Grok, OpenCode Go, Cursor) by translating Anthropic‑style API calls, handling auth, routing, streaming and offering a TUI monitor.