← 开源
notatestuser

ds4-control

macOS menubar app for fast local DeepSeek V4.1, with 1M context.

ApplicationsPersonalWrappersSwift
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
915
Star
15
Fork
+-1
本周
2
贡献者
创建于 2026-05-29 · 更新于 2026-10-12 · 今日第 12669 名
主要开发者
notatestuserjacquerie

notatestuser/ds4-control 排名第 12,669,有 915 个星标。

同类别比较

notatestuser/ds4-control 排名第 12,669,此处有 8 个同类条目;robusta-dev/kubernetes-chatgpt-bot 排名第 12,670。

同类别比较
名称排名指标
Shy2593666979/AgentChat12,652
语言:
Python
星标数:
917
分叉数:
114
简介:
AgentChat 是一个基于 LLM 的智能体交流平台,内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作,Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术,实现高效的知识检索与工具调用,使用 FastAPI 构建高性能后端服务。
SkywalkerDarren/chatWeb12,653
语言:
Python
星标数:
917
分叉数:
135
简介:
ChatWeb can crawl web pages, read PDF, DOCX, TXT, and extract the main content, then answer your questions based on the content, or summarize the key points.
williamfzc/chat-gpt-ppt12,657
语言:
Go
星标数:
917
分叉数:
86
简介:
Use ChatGPT (or other backends) to generate PPT automatically, all in one single file.
paulfitz/mlsql12,666
语言:
Python
星标数:
916
分叉数:
67
简介:
inferring sql queries from plain-text questions about tables
robusta-dev/kubernetes-chatgpt-bot12,670
语言:
Python
星标数:
915
分叉数:
98
简介:
A ChatGPT bot for Kubernetes issues.
amor71/LiuAlgoTrader12,676
语言:
Python
星标数:
913
分叉数:
149
简介:
Framework for algorithmic trading
autowarefoundation/vision_pilot12,677
语言:
C++
星标数:
913
分叉数:
194
简介:
Free and fully open-source L2 ADAS stack powered by End-to-End AI technology
radames/Real-Time-Latent-Consistency-Model12,681
语言:
Python
星标数:
913
分叉数:
116
简介:
App showcasing multiple real-time diffusion models pipelines with Diffusers
关键参数与规格
关键参数与规格
参数值
语言Swift
类别Applications
子类别Personal,Wrappers
关键词Client integration, LocalAI, Memory management, Tool use
星标数915
分叉数15
贡献者2
创建日期2026-05-29
更新日期2026-10-12
1 天星标数0
7 天星标数-1
排名12,669
上次排名12,585
排名变化-84
7 天星标排名17,443
上次 7 天星标排名17,413
7 天星标排名变化-30
总星标排名11,915
上次总星标排名11,892
总星标排名变化-23
README 摘录

DS4 Control A macOS menu bar pane for **DeepSeek V4** and **V4. It launches, supervises, and monitors a local ds4 server, lets you pick **V4. 1 Flash**, **V4 Pro (0813)**, or **V4 Flash (0731)** with up to **1M** context, and shows resource use. **Launch Pi, Claude Code or BYOC (Bring Your Own CLI) for local agentic coding. **Pro / Flash selector** with a RAM feasibility checks. **Model downloads** via a built-in native parallel downloader, with a live progress bar and

resume across restarts. **Mini resource widgets**: unified memory, GPU, power, and CPU, sampled on a timer. **Launch Claude Code or Pi** to plan, write, maintain or refactor code. **1M Context** configurable in settings. **Launch on macOS Startup** What it is **not**: No model search or registry browsing. **Auth (optional):** the model repository is public, so no token is required for normal use. RAM feasibility DeepSeek V4 is memory-hungry so DS4 Control gates feasibility before launching. 1 Flash | 41-q2

| ≥ 96 GiB | 341 GiB on disk, ~152 GiB resident main weights + ~189 GiB disk-only Engram. SSD streaming engages automatically on 96–255 GiB (slow: nearly every routed expert streams from disk); full residency on ≥ 256 GiB. 1 Flash | 41-q4 | ≥ 256 GiB | 483 GiB on disk, ~294 GiB resident main weights. SSD streaming on 256–511 GiB; full residency on ≥ 512 GiB. | | V4 Flash (0731) | q4-imatrix | ≥ 256 GiB | Standard. | | V4 Flash (0731) | q2-imatrix | 96 GiB minimum | 96

–127 GiB requires raising the Metal wired limit (see in-app help). Coding Agents It’s suggested to follow the ds4 coding agent setup guide to configure your OpenCode/Claude/Codex/Pi as you prefer. Build & Run For development: To produce a distributable bundle: This builds a release binary and assembles . Signing auto-detects your **Apple Development** identity via and signs the bundle with it. If no Apple Development identity is installed, it falls back to **ad-hoc** signing (the

app runs locally but is not distributable). To sign with your own key: Install an Apple Development certificate (Xcode → Settings → Accounts → Manage Certificates → **+** → Apple Development), **or** Set before running . Three objects do the work, and the SwiftUI layer just observes them: ** ** owns the lifecycle through : it builds the launch arguments, watches stderr for the readiness line, polls for health, and stops gracefully with SIGTERM (SIGKILL fallback). Model weights are fetched by a built-in native parallel downloader (resumable across restarts

). ** ** samples CPU, memory, GPU, and power/ANE via Mach, IOKit, and the private IOReport interface every 2 s, publishing a to the widgets. ** ** turns installed RAM into a variant choice and a budget-derived default context (pure, fully unit-tested). Attribution A big thanks of course to @antirez for antirez/ds4, llama. c and GGML for instrumental foundational work. The resource collectors and widgets are adapted from **mac-resource-monitor**, which in turn credits **macmon** (MIT) for the IOReport power

-sampling approach. The server-supervision pattern is built on the lineage of **mlx-serve**.

常见问题

记录了多少星标和分叉?

notatestuser/ds4-control 有 915 个星标和 15 个分叉。

仓库排名是多少?

notatestuser/ds4-control 排名第 12,669。

记录的语言和类别是什么?

notatestuser/ds4-control 有 915 个星标,语言为 Swift,类别为 Applications。

哪个仓库排名最接近?

notatestuser/ds4-control 与 robusta-dev/kubernetes-chatgpt-bot 比较,后者排名第 12,670,有 915 个星标。

README

DS4 Control

A macOS menu bar pane for DeepSeek V4 and V4.1 via dwarfstar.

It launches, supervises, and monitors a local ds4 server, lets you pick V4.1 Flash, V4 Pro (0813), or V4 Flash (0731) with up to 1M context, and shows resource use.

Launch Pi, Claude Code or BYOC (Bring Your Own CLI) for local agentic coding.

Signed with a live Apple Developer ID & notarized by Apple

Quick Install

brew install --cask ds4-control

Features

  • Start / stop / monitor the local ds4-server child process — spawn, stderr readiness detection, health polling, graceful stop, and crash detection.
  • Pro / Flash selector with a RAM feasibility checks.
  • Model downloads via a built-in native parallel downloader, with a live progress bar and resume across restarts.
  • Mini resource widgets: unified memory, GPU, power, and CPU, sampled on a timer.
  • Launch Chat to talk to the model.
  • Launch Claude Code or Pi to plan, write, maintain or refactor code.
  • 1M Context configurable in settings.
  • Launch on macOS Startup

What it is not:

  • No model search or registry browsing.
  • No embedded inference — all inference is delegated to ds4-server.

Dev quick start

antirez/ds4 is vendored as a git submodule at external/ds4:

git submodule update --init --recursive    # fetch ds4 into external/ds4
bash scripts/apply-ds4-patches.sh           # THINK_MAX prefix (antirez/ds4#635)
make -C external/ds4 -j ds4-server          # build the ds4-server binary
DS4_DIR="$PWD/external/ds4" swift run        # build + run the dev app against the submodule

Requirements

  • Apple Silicon
  • You don't pre-download the model — DS4 Control downloads it for you with a built-in parallel downloader, resumable across restarts.
  • Auth (optional): the model repository is public, so no token is required for normal use.
  • RAM — see below.

RAM feasibility

DeepSeek V4 is memory-hungry so DS4 Control gates feasibility before launching.

Variant Quant RAM Notes
V4 Pro (0813) pro-imatrix ≥ 512 GiB required Anything below is blocked.
V4.1 Flash 41-q2 ≥ 96 GiB 341 GiB on disk, ~152 GiB resident main weights + ~189 GiB disk-only Engram. SSD streaming engages automatically on 96–255 GiB (slow: nearly every routed expert streams from disk); full residency on ≥ 256 GiB.
V4.1 Flash 41-q4 ≥ 256 GiB 483 GiB on disk, ~294 GiB resident main weights. SSD streaming on 256–511 GiB; full residency on ≥ 512 GiB.
V4 Flash (0731) q4-imatrix ≥ 256 GiB Standard.
V4 Flash (0731) q2-imatrix 96 GiB minimum 96–127 GiB requires raising the Metal wired limit (see in-app help).

Performance

Measured single-stream generation throughput on a Mac Studio M3 Ultra (512 GiB):

Model Throughput
V4 Pro (0813) ~14 tok/s
V4 Flash (0731) ~35 tok/s

Varies with context length, prompt, and the Metal wired limit.

Coding Agents

It’s suggested to follow the ds4 coding agent setup guide to configure your OpenCode/Claude/Codex/Pi as you prefer.

Build & Run

For development:

swift run

To produce a distributable bundle:

bash build.sh

This builds a release binary and assembles DS4 Control.app.

First run: open Settings (the gear in the popup) and set the ds4 directory — the folder that contains ds4-server.

Signing

build.sh auto-detects your Apple Development identity via security find-identity and signs the bundle with it. If no Apple Development identity is installed, it falls back to ad-hoc signing (the app runs locally but is not distributable).

To sign with your own key:

  • Install an Apple Development certificate (Xcode → Settings → Accounts → Manage Certificates → + → Apple Development), or
  • Set DS4_SIGN_IDENTITY="Apple Development: …" before running build.sh.

How it works

DS4 Control is a single Swift binary — no embedded inference and no second process language. Three @MainActor objects do the work, and the SwiftUI layer just observes them:

  • SupervisorService owns the ds4-server lifecycle through Foundation.Process: it builds the launch arguments, watches stderr for the listening on http:// readiness line, polls GET /v1/models for health, and stops gracefully with SIGTERM (SIGKILL fallback). Model weights are fetched by a built-in native parallel downloader (resumable across restarts).
  • MetricsManager samples CPU, memory, GPU, and power/ANE via Mach, IOKit, and the private IOReport interface every 2 s, publishing a SystemSnapshot to the widgets.
  • Feasibility turns installed RAM into a variant choice and a budget-derived default context (pure, fully unit-tested).

Attribution

  • A big thanks of course to @antirez for antirez/ds4, llama.c and GGML for instrumental foundational work.
  • The resource collectors and widgets are adapted from mac-resource-monitor, which in turn credits macmon (MIT) for the IOReport power-sampling approach.
  • The server-supervision pattern is built on the lineage of mlx-serve.

License

MIT — see LICENSE.

排名相邻
同类项目