33 results
Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.
Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.
Ollama Cloud models, OpenAI-compatible chat, and Web Search/Fetch for DeepSeek Harness
Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Antigravity IDE quota (default, flash/pro), OpenAI-compatible VLM endpoints, Gemini API, or local Ollama — model-invokable vision tool, wrapper adapters for deepseek/opencode-go, evidence memory, and a polished client panel.
Display-layer translation for the DSH web app: thinking chain, task cards, and optional answer text, in 8 target languages (local Ollama / Google / Bing, fail-open)
ChatGPT Codex, xAI Grok, Zhipu GLM, AWS Kiro, Google Antigravity, Cursor, Ollama Cloud, Kimi, and GitHub Copilot subscription OAuth for DeepSeek Harness — PKCE / device-code / Google login, local Responses proxy, llm-pi-ai sync.
Ollama native protocol (/api/chat) provider for DeepSeek Harness: llm-ollama settings namespace, serving LlmAdapter, /api/tags model discovery, and a whole-page Ollama settings section.
DeepSeek Harness plugin that enhances custom provider setup by auto-discovering models and auto-populating contextWindow, maxTokens, vision, and reasoning capabilities from models.dev
Adaptive image routing for DeepSeek Harness: pass images directly to native multimodal models and transcribe them only for text-only models.
DeepSeek Harness plugin for local GGUF models without Ollama
Eyes for text-only DeepSeek: view_image tool (any OpenAI-compatible VLM, local Ollama or cloud) + chat image-attachment bridge that rewrites pasted/dropped images into view_image path markers
Local-first RAG knowledge tools for DSH: kb_query / kb_ingest / kb_crawl / kb_related, backed by the kb-rag Python pipeline (Ollama bge-m3 + ChromaDB + SiYuan). Zero API cost, data never leaves your machine.
Raise Node's HTTP timeouts for the whole DeepSeek Harness process so slow local models are not cut off at 5 minutes
Universal local vision bridge tool for DSH: describe/answer questions about images via any OpenAI-compatible local inference framework (llama.cpp / Ollama / LM Studio / vLLM), vision models auto-detected
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, ...).
DSH 插件：可接入识图模型 API（本地大模型识图工具 + 设置界面）。配置 OpenAI 兼容的识图接口（LM Studio / vLLM / Ollama 等），接口留空即不启用识图模型。
自包含的 DeepSeek Harness 视觉系统：DeepSeek 视觉孪生路由（原生图片体验 + 视觉桥请求层拦截）+ 本地 Ollama Agentic Vision 工具（describe/OCR/结构化扫描/区域查询/元素定位/双图对比/剪贴板）+ 粘贴分流（paste-to-path）。安装即用，无本机路径依赖。
Ollama-backed search provider for the DeepSeek Harness web capability seam (ctx.web): adapts Ollama /api/web_search into dsh web_search tool.
DSH 本地视觉能力：macOS Vision OCR + ollama qwen3-vl 语义描述 + 上传图片桥接（图片块转文本，text-only 通道可用）
本地图片理解插件：vision Service + vision_describe 工具（MiniMax-M3 → 智谱 GLM-4.6V-Flash → 本地 Ollama gemma3:4b 三层降级链）
Ordered, extensible web-search fallback chain for DeepSeek Harness.
Ollama 监控与测评平台：node 半侧提供 DSH 工具，web 半侧提供设置页内的交互面板
DSH vision bridge (DSH >= 0.1.2-rc.1): when the selected chat model is text-only, attached images are described by a local Ollama VL model (qwen3-vl:8b) with keep_alive VRAM cooling. Install-time patch of dsh-api-session-controller prompt admission + runtime status companion.
Local OpenAI-compatible model-server discovery + tiered reasoning-metadata resolution for DeepSeek Harness (dsh).