{
  "schema_version": "1.1",
  "id": "s9:https://github.com/Alishahryar1/free-claude-code",
  "slug": "free-claude-code-02z06gq",
  "url": "https://feed7.dev/p/free-claude-code-02z06gq",
  "title": "Alishahryar1/free-claude-code",
  "why_included": "Free Claude Code is a local proxy that lets Claude Code, Codex, and Pi use cloud or local models through native pickers. It broadens model choice, but adds a credential-bearing gateway to audit and maintain.",
  "summary": "Free Claude Code routes Claude Code, Codex, and Pi through **31 cloud and local providers** from a local Admin UI. It preserves model selection, streaming, tools, reasoning controls, and image input where providers support them, with optional IDE and messaging integrations.",
  "practical_implication": "Use it when you need provider portability or want to compare models without replacing your coding-agent clients. Prefer tool-capable models with sufficient context, protect the proxy with token authentication, and review the installer and generated client configuration before use.",
  "agent_context": "Free Claude Code routes Claude Code, Codex, and Pi through **31 cloud and local providers** from a local Admin UI. It preserves model selection, streaming, tools, reasoning controls, and image input where providers support them, with optional IDE and messaging integrations.\n\nUse it when you need provider portability or want to compare models without replacing your coding-agent clients. Prefer tool-capable models with sufficient context, protect the proxy with token authentication, and review the installer and generated client configuration before use.\n\nCompatibility varies by provider, and unsupported reasoning controls fall back to provider behavior. The proxy stores credentials, changes endpoint configuration, and can expose agent sessions through Discord or Telegram, expanding the security and maintenance surface.",
  "source": {
    "name": "GitHub",
    "url": "https://github.com/Alishahryar1/free-claude-code",
    "published_at": null
  },
  "source_class": "tool",
  "content_type": "GitHub Repo",
  "layer": "tools",
  "domains": [
    "coding"
  ],
  "topics": [
    "coding-agents",
    "model-selection",
    "gateways"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "Compatibility varies by provider, and unsupported reasoning controls fall back to provider behavior. The proxy stores credentials, changes endpoint configuration, and can expose agent sessions through Discord or Telegram, expanding the security and maintenance surface."
  ],
  "connected_context": {
    "meaning": "This broadens provider portability at the client boundary: existing coding agents can compare many cloud and local models without adopting a single managed gateway. That flexibility shifts routing, compatibility testing, credential custody, endpoint changes, and messaging exposure onto the operator, so provider count is not evidence of equivalent capability, reliability, or security.",
    "corpus_size": 340,
    "generated_at": "2026-08-04T10:04:31.651Z",
    "connections": [
      {
        "title": "Introducing Cursor Router",
        "source_name": "Cursor",
        "source_url": "https://cursor.com/blog/router",
        "feed7_url": "https://feed7.dev/p/router-0enx7s0",
        "reason": "Cursor Router automates model choice by task and cost, whereas Free Claude Code primarily exposes provider and model choice to the operator; portability does not itself supply routing quality."
      },
      {
        "title": "Kimi K3 and Kimi K3 Fast with ZDR and US-based providers now on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/kimi-k3-and-kimi-k3-fast-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/kimi-k3-and-kimi-k3-fast-on-ai-gateway-0jpdaz6",
        "reason": "Kimi’s managed routes expose explicit speed, residency, retention, and fallback choices, highlighting operational guarantees that a multi-provider local proxy must verify separately for each backend."
      },
      {
        "title": "AI Gateway adds unified fast mode support",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/ai-gateway-adds-unified-fast-mode-support",
        "feed7_url": "https://feed7.dev/p/ai-gateway-adds-unified-fast-mode-support-144dq26",
        "reason": "Vercel normalizes fast-mode requests and fallback behavior across supported models; Free Claude Code preserves controls only where providers support them and otherwise inherits provider-specific behavior."
      },
      {
        "title": "The Base Model Is Dead — Varun Singh, Arcee AI",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=xbPriQWXtWM",
        "feed7_url": "https://feed7.dev/p/the-base-model-is-dead-varun-singh-arcee-ai-02hts76",
        "reason": "The pre-training discussion reinforces the need for workload testing across the proxy’s many models: common client controls and large provider coverage do not reveal each model’s underlying task-skill distribution."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": null,
  "modified_at": null,
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/free-claude-code-02z06gq",
    "json": "https://feed7.dev/p/free-claude-code-02z06gq.json",
    "markdown": "https://feed7.dev/p/free-claude-code-02z06gq.md"
  }
}