35 results
A vision bridge for text-only DeepSeek Harness models: registers an `analyze_image` tool that answers questions about images via ANY OpenAI-compatible vision/multimodal endpoint (SiliconFlow, DashScope, Zhipu, OpenRouter, Ollama, ...).
Local web fetch provider: fetches web pages and summarizes/parses them with the local Ollama model before returning to the agent
Automatically resumes replies cut off at the output token limit — built for self-hosted Ollama users with small output caps. · 回答被输出上限截断时自动发送"继续"续写，面向自部署 Ollama 小上限场景。
让用户个人/本地 LLM 接入 DeepSeek Harness：Ollama、KoboldCpp、LM Studio 及任意 OpenAI 兼容端点作为本地冗余算力，本地优先处理一部分信息，难点才交给云端主模型。充分利用本地算力并节省 token。
A project-scoped multimodal video director plugin for DeepSeek Harness.
Probe local model servers (llama.cpp / Ollama) for the real runtime context window and keep llm-pi-ai's contextWindow in sync automatically — tighter before overflow, wider when the server grows. Zero-config profile plugin for DeepSeek Harness.
Automatic reasoning and image capability detection for custom DeepSeek Harness models
Cherry Studio-style knowledge base system for DeepSeek Harness (DSH): bases, documents, chunking, embeddings (OpenAI-compatible / Ollama / local / lexical fallback), retrieval, model-facing tools, and a browser management panel
DeepSeek Harness 外置视觉模型插件：inspect_image 把本地图片或 http(s) 图片 URL 发给任意 OpenAI 兼容端点，视觉模型看图的文字回答直接带回对话；附 Web UI 设置栏。
Zero-config local vision and realtime audio routing for DeepSeek Harness
Ordered, extensible web-search fallback chain for DeepSeek Harness.