基于dsh web实现的多种模式，目的是服务于redteam进行授权的安全研究，覆盖渗透测试、红队评估、代码审计等范围领域，请勿用于非法行为。（允许二开，赋予模块各位自己的业务逻辑，方法论只有自己熟练的才好用，好的方法论=好的生态）

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks. Website: https://apirelayaudit.com

Sign in with ChatGPT inside DeepSeek Harness, and use your ChatGPT subscription to serve models.

Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.

DeepSeek Harness 破甲：让所有模型都能破甲，不同模型可换不同提示词；默认提示词面向国模「小码酱」。Jailbreak for every model — swap prompts per model. 求 Star 收藏 ⭐ 如要二开，请查看署名要求部分

Use openai-codex models and image generation via ChatGPT OAuth for DeepSeek Harness.

Google Antigravity (agy CLI) models for DeepSeek Harness — streaming chat, thinking, tool activity, usage, in-GUI Google OAuth login

Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)

Access gate for AI coding harnesses (DSH plugin + Claude Code hook): per-directory deny/read/full, roster groups, audit log, model-facing tools with owner-approved widening.

Google Antigravity (agy) OAuth auth + model access plugin for DeepSeek Harness: multi-account pool, 429 rotation, device fingerprinting, CLI and web login.

Use a Kimi Code membership in DeepSeek Harness through a dedicated Kimi subscription model route