Sugt — AI skill for Claude Code
SUGT - local AI gateway & skills console.
How to install Sugt
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open lsuen/sugt and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Sugt does
SUGT - local AI gateway & skills console. Centralize LLM API keys, one OpenAI/Anthropic-compatible proxy for Claude Code, Codex & OpenCode. Homebrew & winget. Fully open source (Apache-2.0).
Alternatives in AI
- WindsurfAPI — Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, A 3k ★
- Vllm Mlx — High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon 1.5k ★
- CliRelay — Self-hosted AI gateway for coding CLIs — one OpenAI/Claude/Gemini/Codex-compatible endpoint, with a multi-tena 1k ★
README
SUGT — Local AI Gateway & LLM Skill Console
Heads-up: my day job took a hit recently and I'm looking at delivery gigs for a while — updates will be sparse. The code is fully open source; fork it and play. Stars are few and I'm not chasing traffic — if this helped you and you're willing, a share would mean a lot.
**SUGT (su gateway)** is a local AI gateway and skills control plane for your desktop. It centralizes API keys from multiple LLM providers (OpenAI, Anthropic, ModelScope, Volcengine, SiliconFlow, Moonshot Kimi, DeepSeek, DashScope, and self-hosted) behind a single OpenAI / Anthropic-compatible proxy, so Claude Code, Codex, OpenCode, and other AI coding clients all talk to one local endpoint — while you swap upstream models in a single panel. It also ships a Skills console for discovering, installing, and mounting Skills without losing your library.
- One key set, everywhere: Base URLs and auth are consolidated into one local gateway.
- Swap upstreams freely: OpenAI, Anthropic, ModelScope, Volcengine, SiliconFlow, Moonshot Kimi, DeepSeek, or your own models — no client-side reconfiguration.
- Skills that stick: discover, install, and mount Skills; unmounting never loses your library.
| Author | Sun Wenlong · 异常设计 |
| Open source | Apache-2.0, fully open source |
| Releases | GitHub Releases |
中文文档:[README.zh.md](README.zh.md)
License
The release on [GitHub Releases](https://github.com/lsuen/sugt/releases) is the full product: local AI gateway, protocol translation, client takeover, Skills console, and the in-app Me companion. Source is Apache-2.0.
Why
- API keys scattered across Open
Related Skills
Nano LLM Proxy
Tiny single-binary LLM gateway — pool multiple providers and API keys behind one OpenAI/Anthropic-compatible e
LLM Rate Limit Proxy
Self-hosted LLM proxy that pools and rotates your API keys, queues requests instead of returning 429 Too Many
Req LLM Gateway
OpenAI-compatible LLM proxy with telemetry and multi-provider routing
ZAAFPulse
ZAAFPulse: local-first AI command center. Usage, cost and quality signals (accuracy, relevance, faithfulness,
Token Proxy
Local AI API gateway for OpenAI / Gemini / Anthropic. Runs on your machine, keeps tokens counted (SQLite), off
AI Gateway
Custom AI reverse-proxy gateway: routes Anthropic/OpenAI agents (Hermes, Claude Code) through residential prox
Related Agents
Session Error Analyzer
Analyzes specific AI IDE sessions (Claude Code, OpenAI Codex, OpenCode) for LLM behavior errors and returns a
Grok Agent 01
ONLY job: find free or freemium AI token/API plans (OpenAI-compatible, Anthropic, Google, open routers, studen
Codex CLI
Codex CLI → any OpenAI-compatible endpoint