AI CLI-to-API proxy
A Go proxy server that exposes AI coding CLIs (Antigravity, ChatGPT Codex, Claude Code, Grok Build, etc.) as OpenAI/Gemini/Claude/Codex-compatible API endpoints for standard API clients and SDKs.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Choose when you would rather run a JavaScript/Node proxy under GPL-3.0 than the seed's Go/MIT proxy.
Self-hosted multi-protocol AI API proxy for Antigravity, Codex, Grok, Kiro, OpenAI, Claude, and custom providers. Supports OpenAI-compatible API, Claude API, Gemini protocol conversion, GPT, Grok Build, Claude Opus, Gemini Pro, Kimi, MiniMax, provider pools, smart routing, and automatic failover.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose when you want a TypeScript control point that lets Codex/Claude Code clients use arbitrary upstream API providers instead of exposing CLI logins to API clients.
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Choose when you need per-agent local routing/orchestration across model providers instead of a serverized CLI-to-API adapter.
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
Choose when you already have upstream API keys and want a broad self-hosted one-endpoint model gateway instead of wrapping CLI subscriptions.
Never stop coding. Free MIT AI gateway: one endpoint, 359 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by hundreds of contributors
These projects were analysed and named CLIProxyAPI among their alternatives. The relationship is not symmetric — how CLIProxyAPI rates them is a separate judgement, made when CLIProxyAPI is analysed in its own right.
calls CLIProxyAPI “Use it when you prefer a Go-based proxy that turns free subscription backends into compatible APIs and don't need 9Router's token-saver.”
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.
calls CLIProxyAPI “Go-based proxy with built-in support for Antigravity, Codex, and Grok; pick for single-binary deployment and native performance.”
Self-hosted multi-protocol AI API proxy for Antigravity, Codex, Grok, Kiro, OpenAI, Claude, and custom providers. Supports OpenAI-compatible API, Claude API, Gemini protocol conversion, GPT, Grok Build, Claude Opus, Gemini Pro, Kimi, MiniMax, provider pools, smart routing, and automatic failover.
calls CLIProxyAPI “Wraps free/pro coding CLIs (Antigravity, Codex, Grok) into compatible APIs; choose when you want to tap those free tiers via their CLI rather than public provider APIs.”
Never stop coding. Free MIT AI gateway: one endpoint, 359 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by hundreds of contributors
calls CLIProxyAPI “when your upstreams are consumer coding CLIs rather than official provider APIs”
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
calls CLIProxyAPI “Choose when you need to expose subscription endpoints of coding CLIs as standard APIs without running a full agent control plane.”
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
calls CLIProxyAPI “Choose it when your budget is your own Codex/Claude/Gemini subscriptions instead of per-token USDC — single Go binary, no payment rails.”
The agent-native LLM router for autonomous agents. Every frontier model behind one wallet, <1ms local routing, USDC payments on Base & Solana via x402.
calls CLIProxyAPI “Choose when you hold Antigravity/ChatGPT Codex/Claude Code/Grok Build subscriptions and want to expose them as a local OpenAI/Gemini/Claude-compatible API.”
免费大模型API，支持免费调用GPT、DeepSeek等主流模型，免费额度10000点，每日刷新！另付费价格最低官方1-2折！
calls CLIProxyAPI “when your upstreams are consumer coding CLIs (Codex, Antigravity, Claude Code) rather than provider API keys with failover.”
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.