Modelos y proveedores

Codex web search provider for DeepSeek Harness (DSH)

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM calls, and tracks per-model token consumption with a feedback-driven ranking.

Ollama Cloud native chat adapter: direct NDJSON translation of the Ollama /api/chat wire format, model discovery with context windows and capabilities, and web search/fetch providers under the ollama-cloud id, plus a Web settings card.

Coding-subscription OAuth for SuperGrok/Grok Build, ChatGPT Plus Codex, Kimi Code and Claude Code, plus an opt-in loopback OpenAI/Anthropic gateway: local login without pasting tokens, AUTH refresh-and-retry, grok-4.6 xhigh, and API-key route coexistence.

Writes live provider model lists into DSH settings and shows 5h/7d plan windows or metered balance for the current session model.

macOS Keychain credential provider that replaces the local-file provider and uses a signed, notarized universal helper.

Use your ChatGPT/Codex subscriptions in DSH, with image generation and web search support.

Plugin de proveedor Command Code para DeepSeek Harness (dsh): funciona con todos los planes de Command Code, incluido el plan Go de 1 dólar; usa la clave de API de autenticación de Studio a través de /alpha/generate, no la API de Provider

Proveedores de búsqueda y obtención web respaldados por fastCRW para DeepSeek Harness (ctx.web)

Usa suscripciones de ChatGPT (Codex), Claude y Grok (X Premium) como proveedores de LLM en DeepSeek Harness, con inicio de sesión OAuth desde la página de ajustes web

Plugin de DeepSeek Harness: consulta el saldo/uso de AI Monitor desde SQLite local; un agente consciente de los costes, con contabilidad automática mediante el proxy de AI Monitor.

Proveedor de búsqueda web respaldado por SearXNG para la interfaz de capacidad web de DeepSeek Harness (ctx.web): metabúsqueda autoalojada, sin clave de API, sin consumir un turno del modelo por cada búsqueda

Plugin de DeepSeek Harness: proveedor de búsqueda web respaldado por AnySearch (agrega exa/tavily/firecrawl a través de una única pasarela MCP), registrado en ctx.web.

Soporte de proveedor Claude personalizado para DeepSeek Harness

Paquete de proveedor de búsqueda Tavily para DeepSeek Harness (dsh): registra un WebSearchProvider en ctx.web

Plugin de proveedor de DSH para acceder a Codex a través de una suscripción de ChatGPT.

Google Antigravity / Cloud Code Assist model provider for DSH with native Web OAuth, real-time quota tracking, and dynamic reasoning effort routing.

DSH CPA provider and runtime plugin

Unofficial OpenAI Codex provider for DeepSeek Harness with ChatGPT subscription sign-in.

NeevSandbox execution providers for DeepSeek Harness

Silence Chrome/iCloud password-manager prompts over DeepSeek Harness API-key inputs: rewrites password-type secret fields into masked text fields so browser password managers never treat DSH API keys as account passwords.

LLMTR AI gateway provider for the DeepSeek Harness LLM seam: 170+ chat models and Türkiye-hosted LLMs behind one OpenAI-compatible key

DeepSeek Harness bundle that registers Claw Orchestrator as an ACP subagent provider — delegate a dsh subagent to a multi-engine council across Claude Code, Codex and Cursor.

DeepSeek Harness 高峰期模型自动切换插件：高峰前自动切到指定替代模型，高峰后切回官方模型。· Auto-switch to an alternate model before DeepSeek peak hours and back to the official model afterwards. · 本插件由 AI 全权开发，作者无编程经验，请自行测试安全性；安装说明可能含 AI 幻觉。· Developed by AI; test at your own risk; install