justlovemaki/AIClient2API Alternatives

AI API proxy / model aggregation for coding agents

Self-hosted multi-protocol AI API proxy that converts client-only AI model APIs (Antigravity, Codex, Grok, etc.) into an OpenAI-compatible endpoint for coding tools.

8.8kJavaScriptGPL-3.0active · last push 20d agoGitHub

Drop-in peers

Same problem, same approach. Swapping one for another is a config change, not a rewrite.

Sort

diegosouzapw/OmniRouteGitHub

MIT-licensed and supports over 350 providers; pick for broader provider coverage and permissive licensing.

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

: 72.7k
: TypeScript
: MIT

active4d ago

musistudio/claude-code-routerGitHub

Local control plane with advanced routing and orchestration for Claude Code; pick if your workflow centers on Claude Code and needs plugin-like extensibility.

One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.

: 37.2k
: TypeScript
: MIT

active22d ago

kittors/CliRelayGitHub

Go implementation with built-in web console, request logs, and quotas; pick for a lightweight gateway with out-of-the-box usage management.

Self-hosted AI gateway for coding CLIs — one OpenAI/Claude/Gemini/Codex-compatible endpoint, with a multi-tenant web console, request logs, and spend quotas.

: 1.0k
: Go
: MIT

active17d ago

router-for-me/CLIProxyAPIGitHub

Go-based proxy with built-in support for Antigravity, Codex, and Grok; pick for single-binary deployment and native performance.

Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build, Muse Code, Davin as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini Series, GPT Series, Grok Series, Claude model through API

: 52.5k
: Go
: MIT

active17d ago

caozhiyuan/copilot-apiGitHub

Gateway for GitHub Copilot/Codex with OpenAI and Anthropic compatibility; choose if you primarily use Copilot-based accounts.

GitHub Copilot, OpenAI Codex, OpenCode Go, and third-party AI provider gateway with OpenAI and Anthropic API compatibility.

: 1.0k
: TypeScript
: MIT

active17d ago

decolua/9routerGitHub

JavaScript router with 40+ free providers and auto-fallback; pick for unlimited free coding with aggressive fallback handling.

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.

: 29.4k
: JavaScript
: MIT

active18d ago

lidge-jun/opencodexGitHub

Focuses on exposing Codex CLI/SDK to any LLM via a universal proxy; choose when Codex is your primary client.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

: 15.5k
: TypeScript
: MIT

active16d ago

dwgx/WindsurfAPIGitHub

Self-hosted reverse proxy for Windsurf/Devin models; choose when using those IDEs instead of Antigravity/Codex.

Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, Anthropic- & Gemini-compatible APIs. Zero-dependency self-hosted reverse proxy for Claude Code, Cline & Cursor. 把 Windsurf/Devin 云端 100+ 模型变成三套兼容 API。

: 3.0k
: JavaScript
: MIT

active16d ago

askalf/darioGitHub

Local proxy leveraging Claude/ChatGPT subscriptions; pick if you have those subscriptions and want a simpler wire-compatible server.

Use your Claude and ChatGPT subscriptions in Cursor, Cline, Aider, Claude Code and the Agent SDK — at subscription pricing, not per-token API bills. One local Anthropic + OpenAI-compatible endpoint: either plan answers either wire shape, auto-failover when one hits its limit, multi-seat pooling, live Claude Code drift tracking.

: 542
: JavaScript
: MIT

active17d ago

funny-vibes/agent-vibesGitHub

Unified gateway to expose Antigravity/Codex as Anthropic/OpenAI APIs; choose for minimal protocol translation to Claude Code/Cursor.

Unified Agent Gateway — Enables Claude Code CLI and Cursor IDE to use free AI backends (Antigravity, Codex) through protocol translation

: 361
: TypeScript
: MIT

active20d ago

ink1ing/anti-apiGitHub

Zero-dependency proxy converting Antigravity/Codex/Copilot to OpenAI/Anthropic API; pick for a simple TypeScript implementation.

Turn Antigravity / codex / github copilot into Anthropic & Openai API compatible server. Usable with Claude Code / Xcode etc.

: 519
: TypeScript
: MIT

active21d ago

Same job, different approach

Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.

Sort

BerriAI/litellmGitHub

General-purpose LLM gateway with cost tracking and guardrails for API providers; choose over seed only if you don't need client-only API emulation.

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]

: 60.1k
: Python
: NOASSERTION

active2d ago

xiaoY233/Chat2APIGitHub

Converts official web UIs from DeepSeek/GLM/Kimi into APIs; pick when your free sources are web UIs, not client-only IDEs.

Chat2API enables zero-cost access to leading AI models by leveraging official web UIs. It supports providers such as DeepSeek, GLM, Kimi, MiniMax, Qwen, and Z.ai, and seamlessly integrates with tools like openlcaw, Cline, and Roo-Code.

: 1.6k
: TypeScript
: NOASSERTION

active4mo ago

experientiallabs/experientialGitHub

Open-source model gateway for closed/open/local models; pick for a unified control plane across all model types without client-only simulation.

Experiential is the open source, zero markup gateway for BYOK, self-hosted and 1000+ marketplace models. It learns from your traffic to cut costs, recommend better models, and train a specialized model you own.

: 5.3k
: Python
: Apache-2.0

active16d ago

Older generation, or narrower

An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.

jwadow/kiro-gatewayGitHub

Single-provider gateway for Kiro IDE; valid if you only need Kiro and want a tailored lightweight solution.

👻 Proxy API gateway for Kiro IDE & CLI (Amazon Q Developer / AWS CodeWhisperer). Use free Claude models with any client.

: 2.2k
: Python
: AGPL-3.0

active5mo ago

Listed as an alternative to

These projects were analysed and named AIClient2API among their alternatives. The relationship is not symmetric — how AIClient2API rates them is a separate judgement, made when AIClient2API is analysed in its own right.

router-for-me/CLIProxyAPIGitHub

calls AIClient2API “Choose when you would rather run a JavaScript/Node proxy under GPL-3.0 than the seed's Go/MIT proxy.”

52.5kGoactive

decolua/9routerGitHub

calls AIClient2API “Use it if GPL-3.0 is acceptable and you need client-to-API protocol conversion across Antigravity, Codex, Grok and custom providers.”

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.

29.4kJavaScriptactive

lidge-jun/opencodexGitHub

calls AIClient2API “same class; choose when you need multi-protocol conversion across Antigravity, Codex, Grok, Kiro, Claude, and custom providers.”

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

15.5kTypeScriptactive

diegosouzapw/OmniRouteGitHub

calls AIClient2API “Self-hosted bridge that re-exposes AI client subscriptions as APIs; pick over OmniRoute when you want to reuse those client access rights rather than catalog public free tiers.”

72.7kTypeScriptactive

BerriAI/litellmGitHub

calls AIClient2API “when you need multi-protocol conversion from AI consumer clients instead of direct provider APIs”

60.1kPythonactive

musistudio/claude-code-routerGitHub

calls AIClient2API “Choose when you need a lightweight self-hosted protocol bridge for many AI clients without CCR's orchestration dashboard.”

One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.

37.2kTypeScriptactive

BeehiveInnovations/pal-mcp-serverGitHub

calls AIClient2API “Pick when you need protocol conversion across OpenAI, Claude, and Gemini in the transport layer rather than in-context model routing.”

The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.

11.8kPythonslowing

BlockRunAI/ClawRouterGitHub

calls AIClient2API “Self-hosted multi-protocol proxy for CLI accounts; take GPL-3.0 and JS runtime if you need Gemini/Claude wire conversion.”

The agent-native LLM router for autonomous agents. Every frontier model behind one wallet, <1ms local routing, USDC payments on Base & Solana via x402.

6.6kTypeScriptactive

chatanywhere/GPT_API_freeGitHub

calls AIClient2API “Choose when you have Antigravity/Codex/Grok/Kiro/OpenAI/Claude client accounts and need a self-hosted multi-protocol conversion proxy.”

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！

42.9kactive

maximhq/bifrostGitHub

calls AIClient2API “when your upstreams are consumer AI clients and you want multi-protocol translation instead of enterprise gateway features.”

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

8.2kGoactive