# Alishahryar1/free-claude-code

Use Claude Code, Codex, Pi, and OpenCode for free (1.3B+ free tokens) from your terminal, app, IDE, or phone like OpenClaw (voice supported + ToS friendly)

Repository: https://github.com/Alishahryar1/free-claude-code
Canonical: https://ross.abutalabs.com/products/free-claude-code
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-27T00:21:49+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 15
- inputs: {"age_days": 217, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 50378, forks 8163 (observed 2026-08-28T04:12:11.756136+00:00)

## What it is
An open-source Python tool that lets you run coding agents like Claude Code, Codex, Pi, and OpenCode against a catalog of 50 ToS-friendly providers offering over 1.3 billion free tokens per month. It works from the terminal, desktop, IDE, or phone, with automatic model failover and token-saving output optimizations.

## Use cases
- use Claude Code for free from my terminal
- connect Codex to free LLM providers
- run coding agents without paying for API tokens
- keep coding when my LLM provider goes down
- reduce terminal output token usage in coding agents
- use one model catalog across multiple coding agents
- access free AI coding assistants from my phone

## When to choose
- you want to use popular coding agents like Claude Code or Codex without paying for tokens
- you need ToS-friendly access to free, paid, subscription, and local models from one place
- you want automatic failover to another model when a provider has an outage
- you work across terminal, IDE, desktop, and mobile and want a unified model setup

## When to avoid
- you need guaranteed enterprise SLAs or dedicated paid inference infrastructure
- you only use a single provider and don't need a catalog or failover
- you require strict data residency or cannot route code through third-party providers
- you need a fully managed cloud service rather than a self-run tool

## Facets
- artifact type: cli-tool
- maturity: active
- function: llm-inference, agent-framework, proxy, developer-tools, cli, chat-interface
- domain: developer-tools, large-language-models
- platform: python, cli, cross-platform, windows
- tags: claude-code, codex, opencode, free-tokens, model-catalog, coding-agents, provider-failover, tos-friendly, token-optimization, ai-agents, command-line, automation, macos, linux

## Member repositories
- Alishahryar1/free-claude-code (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:11.756136+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:19:56.431780+00:00, confidence not recorded.
  - readme: https://github.com/Alishahryar1/free-claude-code (fetched 2026-08-28T04:12:11.756136+00:00, sha f882acb61e44)
- Data as of 2026-08-30T08:39:29.467469+00:00.