模型与 AI 能力

qwen↔DeepSeek bridge: локальная qwen (Ollama) сама маршрутизирует запросы в облачный DeepS

Standalone ChatGPT OAuth account management for DeepSeek Harness.

n8n community node for DeepSeek V4 models (deepseek-v4-flash, deepseek-v4-pro) with thinki

DeepSeek api-key provider authentication and discovery

Provider-neutral LLM service interface for the DeepSeek Harness

DeepSeek controls the panda robotic arm

Visual channel configuration UI for DeepSeek Harness (feishu / imessage / telegram / ...)

DSH 插件 linhoulong123/dsh-client-ui-code-diffs

DSH 插件 Deepseek-R1-1.5B-Ollama-on-NVIDIA-Jetson，暂无作者提供的描述。

DeepSeek-V3, R1 671B on 8xH100 Throughput Benchmarks

DeepSeek api-key provider authentication and discovery

1M-context DeepSeek-V4-Flash inference on NVIDIA Blackwell using sglang and SSD KV cache o

Resumable multi-connection downloader for DeepSeek Harness with China mirror and proxy pre

DeepSeek Harness plugin: gives the agent a voice — it reads completed tasks and attention

A user-friendly DeepSeek AI node, similar to OpenAI, designed to enhance your workflow.

Home Assistant: créditos de OpenRouter y saldo de DeepSeek como sensores nativos (HACS)

ESP32-CAM camera capture and DeepSeek Flash visual recognition demo

Vehicle-robot middleware for the QHXD platform: FastAPI backend on RK3588, Vue 3 dashboard

Home Assistant voice conversation agent for Ollama Cloud, DeepSeek, Groq and Gemini

Local-first, extensible AI agent workspace — FastAPI + Next.js + LangGraph, with skills, M

W4A4 full（VLLM_MOE_W4A4=2）+ （VLLM_B12X_SHARED_WRAPPER=1）+ FlashInfer 0.6.16 + threshold 40

A quantized GGUF reasoning model optimized for local, offline inference with Ollama.

Side-channel image understanding for dsh: the describe_image tool routes one image (file p

豆包视频工坊：把《大肥鱼豆包制作视频》SOP 变成可机检的闸门 —— 风格锁定 / 分镜 12 字段 / 角色卡与参考图分离 / 首尾帧衔接 / 自动配音字幕拼接

Give DeepSeek (text-only) models **vision** in Claude Code and Codex by routing image file

A sleek, ultra-lightweight hybrid LLM chat client built with Next.js (App Router) and Tail

DeepSeek Harness plugin: run subagents on a local llama.cpp model via the OpenAI Responses

DeepSeek-V4-Flash-0731 deployment and benchmarks on 8×RTX 4090 24GB, covering ds4, vLLM, S

Record speech and insert editable text into the conversation draft

Deepseek v4 FIX

小肥鱼 · B站连接器：DeepSeek Harness 插件（只读 B站工具 + 大肥鱼角色卡 + 定时主动开口）

LLM benchmarks on Raspberry Pi 5 (16GB) - Gemma 4, Qwen 3.5, DeepSeek-R1, olmo2 and llama.

Zhipu BigModel all-in-one plugin for the DeepSeek Harness: web search (web_search_prime) +

Scoped MCP resource discovery and reading through shared model tools

Temporary 1017 release badge for official DeepSeek Flash model labels

面向大学生的 DDL 收集、提醒与查看工具：DSH 插件 / Electron 托盘 / 浏览器扩展 / MCP / 本地 OCR。

Open Claude Is Open-source coding-agent CLI for OpenAI, Gemini, DeepSeek, Ollama, Codex, G

DeepSeek-V4.1-Flash (1017) on one 16 GB GPU + 64 GB RAM, experts streamed from NVMe: llama

DeepSeek-V4.1-Flash-1017 compatibility fixes and validated TP4/EP2 serving profile for RTX

VoxConductor — ESP32-S3 desktop intelligent voice hub with LVGL, ASR, DeepSeek, streaming

DeepSeek Messages adapter

Open-weight coding and agent models (Qwen Coder, DeepSeek, GLM, Kimi, Devstral, StarCoder)

Strata 125B MoE + JEV mode: llama.cpp fork with parallel-decision endpoints (yes/no in ~10

Switchless TP4/TP2 for DeepSeek-V4.1-Flash-1017 (uncensored) on DGX Spark (GB10). TensorFo

DeepSeek V4 Flash Vision on 2× RTX PRO 6000: vision at zero cost over 0731. Patches for Fl

Coordinated module and profile configuration hot reload

ESP32-S3 AI voice robot: OLED face, ultrasonic, MX1508 motors, INMP441 mic, MAX98357 speak

Connects DSH to local AI models

Reproducible SGLang image for DeepSeek-V4-Flash-0731 on SM120

DeepSeek-V4-Flash-DSpark optimized vLLM 0.26.0 SM121 dual-GB10 evidence (NVFP4 KV, B12X, D

Jetson Nano edge AI vision Agent Harness: real-time video analytics, MCP tools, event evid

ExpertOnDevice AI com Visão (ESP32-P4/S3) — Agnóstico de LLM (GPT, Claude, DeepSeek, Llama

DeepSeek Harness 聚合语音朗读插件,让小鲸鱼拥有自己的声音

Launch recipes, measured tokens/s and the traps behind them for serving Qwen3.8-Flash-Next

On-device Small Language Model package for Automation Anywhere A360 - CPU inference via ll

DeepSeek Harness 插件：在会话标题栏直接操作 v2rayN 订阅守护（状态面板、一键修复、启停守护、刷新订阅），面板挂 shell.overlay。

Desktop robot on ESP32-S3: voice chat (Baidu STT + DeepSeek + edge-tts), music playback, O

Optional Web bundle for raw Session logs and Chat node inspection

Плагин для DeepSeek Harness (DSH), который убирает ошибку LM Studio в работе с изображения

Reasoning distillation with QLoRA: fine tuning Llama 3.2 3B on reasoning traces distilled

Pure-CUDA engine and OpenAI-compatible server for DeepSeek-V4-Flash-0731-REAP (MXFP4) on J

The invisible hook: a DeepSeek Harness plugin that hooks the llm/stream waterfall — the in

Raspberry Pi home gateway with Mihomo, DeepSeek Harness, guarded operations and reproducib

Configurable, optional skill discovery for DeepSeek Harness: standard catalog, local keywo

Personalized pages and built-in plugin recommendations offered as cards below answers

Tell an AgileX PiPER arm what to do in plain language: GPT-6 Astra or DeepSeek grounds the

AI API gateway / relay: 307 models behind one OpenAI-compatible key. image2.5 $0.0085/imag

AI API gateway / relay: 307 models behind one OpenAI-compatible key. image2.5 $0.0085/imag

AI API gateway / relay: 307 models behind one OpenAI-compatible key. image2.5 $0.0085/imag

AI API gateway / relay: 307 models behind one OpenAI-compatible key. image2.5 $0.0085/imag

AI API gateway / relay: 307 models behind one OpenAI-compatible key. image2.5 $0.0085/imag

AI API gateway / relay: 307 models behind one OpenAI-compatible key. image2.5 $0.0085/imag

🤖 Serverless AI Gateway Bot for Telegram — Connect to 9+ AI providers (Gemini, Groq, OpenR

Whisper speech-to-text provider plugin for DeepSeek Harness (French and 90+ languages, loc

Translate full-length books and documents with Ollama, OpenAI-compatible, Gemini, Mistral,

Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO

Run DeepSeek-V4.1-Flash / DeepSeek-V4-Flash and GLM-5.3-Flash on SM89 (Ada / RTX 4090) and

DeepSeek-V4.1-Flash-1017 on NVIDIA DGX Sparks with TensorFold + EXL3: TP4 (4 Sparks, 93.6

Heterogeneous prefill/decode for DeepSeek-V4-Flash: CUDA prefill (DGX Spark, vLLM) -> Meta

A multi-llm Emacs shell (ChatGPT, Claude, DeepSeek, Gemini, Kagi, Ollama, Perplexity) + ed

Two-node DGX Spark/ASUS GX10 DeepSeek V4 Flash DSpark NVFP4 port for vLLM 0.25, with live

DeepSeek-V4.1-Flash-1017 EXL3 2.9bpw on 2x NVIDIA DGX Spark (GB10) with TensorFold: 2.1-2.

DeepSeek-V4.1-Flash W4A8 optimized vLLM deployment for Ascend 910B (A2) / 910C (A3): patch

DSH 生图插件：火山方舟 / 豆包 Seedream 文生图与图生图，两个模型工具 + 内置技能（Volcano Ark / Seedream image generation

DeepSeek-V4.1-Flash on two NVIDIA DGX Sparks: EXL3 weights from the official checkpoint, u

Local LLM session nodes for ComfyUI that run GGUF models with llama.cpp without external r

Agentic-coding oriented inference engine for N x V100-SXM2, based on SGLang: GLM-5.3-Flash

DeepSeek-V4.1-Flash EXL3 vLLM recipe for 2x DGX Spark (GB10)

A Deepseek V4 Flash 0731 / Vision Exp VLLM stack

DeepSeek-V4.1-Flash inference on NVIDIA Ampere with vLLM, SM80 patches, reproducible throu

Your Ryzen AI Max is running at half speed. SnowLLM: up to 9x faster prefill and 2x faster

A local proxy that connects Cursor to DeepSeek thinking models. 连接 Cursor 与 DeepSeek 推理模型的

Painel de mesa para cotas de IA — Claude, GPT, Cursor, OpenRouter e DeepSeek — rodando em

🚀 Let Codex use any LLM - cost down 30-50x. Support DeepSeek, Zhipu GLM, and any OpenAI-co

GLM-5.2-NVFP4-REAP-469B serving on SM120 (4× RTX PRO 6000 Blackwell) — one-command vLLM la

DSH 插件：同一用例分别跑 AOT 可执行文件与 JIT 启动命令，逐字段对拍 stdout / exit code / stderr / 文件副作用，给出第一处不一致的用例与字

DSH sidebar model shelf: browse connected models by API, bookmark them, and apply one with

See images and search the web from any DSH agent through the live deployment-default API.

DeepSeek Chat Model (reasoning_content fixed)

本地代理，为 DeepSeek API 的安全分类请求关闭思考模式，解决 Claude Code Auto Mode 超时