Unified proxy for AI coding clients β turn Gemini CLI, Claude, Codex, and more into OpenAI-compatible APIs
The fastest local AI engine for Apple Silicon β 4.2x faster than Ollama, drop-in OpenAI replacement.
One unified API proxy for Gemini CLI, Claude Code, Codex, and more β use free tiers via any OpenAI-compatible client
Refreshingly fast local AI server β run LLMs privately on your own GPU or NPU for free
Zero-cost OpenAI-compatible API access to DeepSeek, Kimi, Qwen, GLM and more
Python-free Rust inference server with OpenAI-compatible API for local LLMs β single binary, free forever.
Unified AI Gateway for 100+ LLMs with OpenAI-compatible API
Convert web AI services to OpenAI-compatible APIs with browser automation
API proxy that unifies Gemini CLI, Antigravity, Qwen Code, Kiro into OpenAI-compatible interfaces
