macOS menubar app for fast local DeepSeek V4 Pro/Flash, with 1M context.
-
Updated
Aug 16, 2026 - Swift
#
deepseek-v4-flash
Here are 40 public repositories matching this topic...
⚡️ A community driven PHP client for DeepSeek AI, designed to bring clean API access, fluent developer experience, and framework-friendly integration to PHP applications.
nlp ai text-generation api-client deepseek-coder deepseek-chat deepseek deepseek-api deepseek-v3 deepseek-php-client php-deepseek deepseek-integration deepseek-sdk php-openai-alternative deepseek-php-library deepseek-learning deepseek-r1 deepseek-symfony deepseek-v4-flash
-
Updated
May 24, 2026 - PHP
Fixes missing reasoning_content for DeepSeek V4
proxy cursor reasoning byok deepseek deepseek-reasoner deepseek-v4 deepseek-v4-pro deepseek-v4-flash reasoning-content must-be-passed-back
-
Updated
May 10, 2026 - Python
基于 FastAPI 的 DeepSeek Chat 反向代理，将 DeepSeek 网页版的 API 转换为 OpenAI 兼容格式。 支持流式/非流式对话、专家模式、深度思考（reasoning_content）、工具调用（DSML prompt injection）。 自动处理 PoW 鉴权挑战，无需官方 API Key。
-
Updated
Aug 11, 2026 - Python
DeepSeek V4 Flash CPU/NVMe research fork: 78.62 GiB GGUF validated on 7.7 GiB RAM, CPU-only, using demand paging.
linux mmap moe nvme demand-paging cpu-inference local-llm llm-inference gguf deepseek deepseek-v4 deepseek-v4-flash
-
Updated
Aug 18, 2026 - C
DeepSeek-V4-Flash-0731 284B inference in ~30 GB of RAM on any M-series MacBook
macos swift metal on-device-ai apple-silicon llm llm-inference local-ai on-device-llm deepseek-v4-flash
-
Updated
Aug 18, 2026 - Python
A tool to have multiple claude-code instance with deepseek, minimax, and z.ai glm models
minimax minimax-agent claude-ai deepseek deepseek-api claude-code calude xiaomi-mimo deepseek-v4 glm-5-turbo glm-5-1 deepseek-v4-pro deepseek-v4-flash mimo-v25 mimo-v25-pro glm-5-2
-
Updated
Aug 22, 2026 - TypeScript
Kimi K3, deepseek v4 flash, glm 5.2, qwen 3.8 27b, Muse Glimmer, Nemotron, glm 5.3
website llama website-automation qwen gguf deepseek gguf-models gpt-oss deepseek-v4 deepseek-v4-flash kimi-k3
-
Updated
Aug 22, 2026 - HTML
DeepSeek 逆向 API 支持 Deepseek V4
-
Updated
Apr 27, 2026 - Python
Guide for development with DeepSeek Harness. Building plugin for DeepSeek Harness Project.
deepseek deepseek-api deepseek-v4 deepseek-v4-pro deepseek-v4-flash flaqai deepseek-harness flaq-skills deepseek-harness-plugin deepseek-v4-pro-api deepseek-v4-flash-api deepseek-harness-guide deepseek-harness-skills
-
Updated
Aug 14, 2026
An easy-to-use, reliable DeepSeek Harness desktop app with robust plugin management, process orchestration, dynamic tool discovery, and a selection of useful pre-installed plugins that can be removed at any time.
deepseek deepseek-v4-pro deepseek-v4-flash flaqai deepseek-harness flaq-skills deepseek-harness-plugin deepseek-v4-pro-api deepseek-v4-flash-api deepseek-harness-guide deepseek-harness-desktop
-
Updated
Aug 21, 2026 - TypeScript
Reproducible kit to deploy DeepSeek-V4-Flash-DSpark on a 2× NVIDIA DGX Spark (GB10) cluster: vLLM TP=2 over QSFP 200GbE, NVFP4 KV, DSpark speculative decoding, 1M context, systemd self-heal. Apache-2.0.
cuda rdma nccl vllm llm-inference deepseek gb10 nvfp4 dgx-spark grace-blackwell deepseek-v4-flash tensor-parallel
-
Updated
Aug 19, 2026 - Python
A collection of recipes/notebooks showcasing use-cases of open-source models with Qubrid AI.
llm-api kimi-api deepseek-api openrouter-api gpt-oss-120b openrouter-alternative kimi-k2-6 deepseek-v4-pro deepseek-v4-flash
-
Updated
May 3, 2026 - Python
Codex vision bridge for DeepSeek V4 Flash: give text-only DeepSeek image capability in Codex. Local proxy turns pasted images and view_image into text via free GLM-4V-Flash or any OpenAI-compatible vision API. No GPU, no Ollama.
opencode vision image-to-text codex ai-agent deepseek openai-compatible claude-code responses-api deepseek-v4-flash vision-proxy codex-vision glm-4v-flash
-
Updated
Aug 16, 2026 - Python
DeepSeek-V4-Flash-0731 on 8x RTX 3090 (SM86) with vLLM — verified FP8 serving, benchmarks, build guide, and reproducible release.
multi-gpu fp8 vllm llm-inference speculative-decoding rtx-3090 deepseek-v4 deepseek-v4-flash dspark deepseek-v4-flash-0731 nvidia-ampere sm86
-
Updated
Aug 9, 2026 - Python
Supercharge your daily workflows! Autonomously browse pages, scrape content, switch tabs, fill out inputs, and stream Chain-of-Thought (CoT) reasoning under granular human-in-the-loop safety switches and glassmorphic UI controls.
chrome-extension chrome automation extension ai ai-agents chrome-automation deepseek deepseek-v4 deepseek-v4-pro deepseek-v4-flash
-
Updated
Aug 15, 2026 - JavaScript
A Rust proxy that exposes an **OpenAI Responses API** interface, translating to various upstream backends (DeepSeek, OpenAI, Anthropic) with full streaming SSE support. Built for Codex CLI and similar tools hardcoded to OpenAI.
-
Updated
Jul 11, 2026 - Rust
Unlock Claude Code with DeepSeek V4. Get Anthropic's agent tools with 95% lower costs and local vision.
nodejs proxy api-wrapper cost-optimization ai-agent anthropic-claude ollama lm-studio deepseek anthropic-api ai-coding claude-code vision-llm free-claude-code qwen3-vl deepseek-v4 opus-4-7 deepseek-v4-pro deepseek-v4-flash
-
Updated
Jun 1, 2026 - JavaScript
Improve this page
Add a description, image, and links to the deepseek-v4-flash topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the deepseek-v4-flash topic, visit your repo's landing page and select "manage topics."