#24 · Primary category： AI Gateway & API Infrastructure
AIClient2API
Self-hosted proxy that converts client-only AI model APIs into an OpenAI-compatible gateway, supporting multiple providers and failover.
Project last updated：08/29/26
GitHub Stars
8.7K
Forks
1.4K
Contributors
62
License
GPL-3.0
Why we included this project
Many models ship as client-bound or subscription-only offerings, which makes them awkward to feed into your own dashboards and tooling. AIClient2API gets around that by emulating the requests those client-only front ends (Gemini CLI, Antigravity, Codex, Grok, Kiro) would make and re-exposing the responses behind a standard OpenAI-compatible endpoint, so apps you already run can talk to them without integration rewrites. It also translates between the OpenAI, Claude, and Gemini wire protocols, which matters when different tools in your stack expect different dialects. Account pool management, smart routing, and automatic failover keep it usable at higher load instead of just for quick experiments. If you host something like NextChat or Cherry-Studio and want one gateway in front of a mix of paid and client-gated providers, this is a solid candidate.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
OmniRoute
Open-source AI gateway: one endpoint, 290+ providers (90+ free), 500+ models, auto-fallback, token compression, MCP/A2A, works with Claude Code, Codex, Cursor, Cline, Copilot.
CLIProxyAPI
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.6 Series, Grok 4.5, Claude model through API
kong
🦍 The API and AI Gateway
novu
The open-source communication infrastructure for agents and products
GPT_API_free
Free API for large models, supports GPT, DeepSeek, etc., 10k free points daily, paid plans at 10-20% of official price.