nicremo/dsh-cli

**Let Claude Code, Codex, OpenCode, Pi 또는 다른 에이전트는 DeepSeek 하네스 세션을 병렬로 실행합니다. **

**deepseekharnesscli.nicremo.de **

** Unofficial 커뮤니티 프로젝트. ** dsh-cli는 DeepSeek가 후원하거나 후원하지 않습니다. "DeepSeek 마구"는 DeepSeek의 상표입니다.

왜

연구 및 여러 병렬 세션을위한 DeepSeek 마구 (dsh)를 주로 사용합니다. 기사의 스크린 샷 수집, 블로그 게시물의 스크롤 비디오, 주식 영상. DeepSeek는 빠르고 저렴하며 훌륭한 노동자 풀을 만듭니다. 누락 된 것은 내 주요 코딩 에이전트에 대한 방법입니다. 세션을 시작, 그들을 기다립니다, 결과를 읽으십시오, 따라. dsh-cli는 무엇입니까?

dsh-cli는 ** 시약 첫번째 **입니다. 모든 명령은 비동기이며 한 번에 반환되며, 컴팩트 텍스트 또는 --json를 인쇄하고 안정적인 출구 코드를 사용합니다. Claude Code, Codex, OpenCode, Pi 및 기타 하네스를 가르치는 에이전트 스킬을 발송하여 DeepSeek 하네스로 일하는 방법을 설명합니다.

특징

• **Parallel 연구 배치 ** : dsho research "q1" "q2" ...는 질문 당 한 노동자를 실행; 각은 `report를 쓴다.

Unofficial community project. dsh-cli is not affiliated with, endorsed by or sponsored by DeepSeek. “DeepSeek Harness” is a trademark of DeepSeek and is used here only to describe compatibility.

Why

I use DeepSeek Harness (dsh) mostly for research and for many parallel sessions: ten research questions at once, collecting screenshots of articles, scroll videos of blog posts, stock footage. DeepSeek is fast and cheap, which makes it a great worker pool. What was missing is a way for my main coding agent to drive it: start the sessions, wait for them, read the results, follow up. That is what dsh-cli does.

dsh-cli is agent first. Every command is non-interactive, returns at once, prints compact text or --json, and uses stable exit codes. It ships an Agent Skill that teaches Claude Code, Codex, OpenCode, Pi and other harnesses when and how to delegate work to DeepSeek Harness.

Features

• Parallel research batches: dsho research "q1" "q2" ... runs one worker per question; each writes report.md and sources.json, dsho collect merges them into one INDEX.md.
• Material gathering: dsho materials "brief" runs one worker per kind (screenshots, scroll videos, news articles, stock footage, stock photos) with a manifest.json that records source and licence for every file.
• Live in the DSH web UI: when dsh web is running, every job is a real session in that UI. A batch becomes its own workspace, every session gets a readable title, and you can watch or step in.
• Headless fallback: without the UI, each job runs in its own headless dsh process with a lean profile (orchestra) that reuses your research MCP servers.
• Steer like a human would: wait, status, logs -f, result, files, continue (same session, same folder), cancel.
• Deterministic captures: dsho capture shot|scroll takes clean screenshots and smooth 1080p scroll videos with Playwright (cookie banners dismissed, overlays hidden, ad networks blocked, watchdog for hanging pages).