llm-adapter

Live request metadata minimization for DeepSeek Harness, covering the native DeepSeek provider with WebUI settings.

LongCat (LongCat-2.0) provider for DeepSeek Harness — 1M context, thinking mode, tool calling

DeepSeek Harness plugin: run subagents on a local llama.cpp model via the OpenAI Responses (/v1/responses) protocol — LLM adapter + delegation skill

DeepSeek Harness (dsh) LLM adapter backed by aimux — one Rust engine, 325+ providers as dsh model routes

Kimi (Moonshot AI) LLM adapter plugin for DeepSeek Harness — three routes: kimi-code (Kimi Code subscription), kimi-cn, kimi-global. Streaming, thinking mode, tool calling, image input, plus a built-in Kimi settings page.

FriendliAI serverless LLM adapter for DeepSeek Harness — OpenAI-compatible chat completions with dynamic model discovery and reasoning

该仓库暂未提供项目说明。

DeepSeek relay station adapter for deepseek-harness with reasoning-effort control

Bailian (DashScope) Kimi LLM adapter plugin for DeepSeek Harness — kimi-k3 with image input, thinking and tool calling. No build step.

该仓库暂未提供项目说明。