dsh-llm-chatgpt-web
ChatGPT Web (owned Chromium driving Temporary Chat) adapter for the DeepSeek Harness LLM seam
129 results
ChatGPT Web (owned Chromium driving Temporary Chat) adapter for the DeepSeek Harness LLM seam
Universal bridge adapter for DeepSeek Harness: consume external MCP servers & Agent Plugins 1.0, and expose DSH native tools back as an MCP server.
DeepSeek Harness plugin: a Session-header control that detects how a workspace is meant to be run, and runs it. Node.js adapters today, any environment through user-defined commands.
ChatGPT-powered coding, image generation and web search for DeepSeek Harness, with account and usage settings.
Free OpenCode Zen models for DeepSeek Harness (DSH): native dsh-llm adapter plugin, no API key.
Volcengine Ark (火山方舟) Agent Plan and Coding Plan model routes for DeepSeek Harness: two ready provider profiles declared on the shipped llm-pi-ai adapter, a session-header pill showing each plan's remaining allowance and when it next refreshes, and a Settings page that enables or disables individual models in the model selector.
A dsh plugin that replaces the built-in llm-pi-ai and llm-deepseek adapters, the model selector and the Models settings page with self-maintained versions, tracks upstream @earendil-works/pi-ai, and adds quota/balance lookups plus a provider management UI
dsh plugin: shows the model name the upstream actually reported for each assistant step, backfilling pi-ai replay metadata from a non-invasive fetch observer when the adapter omits it
Use the Jev (System One) decision-model paradigm with any OpenAI-compatible LLM — no TypeSafe key required. Registers a jev_decide tool on DeepSeek Harness (dsh).