플러그인

Quantitative R&D toolkit for DeepSeek Harness — 46 tools across six domains covering market data, indicators, factor evaluation, walk-forward ML validation, risk, options, bonds and fund simulation, with an end-to-end research pipeline.

BitFun과 DSH 사이의 ACP 브리지입니다.

Dead-code detection for AI-generated codebases: graphlint builds a dependency graph, finds code unreachable from any entry point to enable codebase cleanup and functional‑effectiveness understanding, and exposes graphlint_query / graphlint_build / graphlint_config tools plus a graphlint skill to DSH agents.

사용자 승인을 받은 소스 코드로부터 Functions, MCP 도구, 워크플로 Skills, 오프라인 테스트 패키지를 생성

DeepSeek Harness용 재미있는 플러그인 모음입니다.

Multi-provider account balance display for the DeepSeek Harness Web GUI. Queries real billing APIs (DeepSeek, StepFun, Kimi Coding, OpenRouter, MiniMax, xAI) and shows balance/quota in front of the model selector. Providers without an API-level billing en

Turns coding into an RPG: finished turns, tool calls and completed todos earn XP, with 27+ achievement badges, levels, titles and seasons. Event-driven scoring with a pure-function engine — the work itself is the game.

DSH 플러그인: @firecrawl/anydoc 기반으로 Word, PPT, Excel, PDF, EPUB, CSV 등 문서를 GitHub-Flavored Markdown으로 변환

DSH 시세 티커 플러그인입니다: 원하는 종목을 선택할 수 있는 암호화폐/환율/A주/지수/홍콩·미국 주식 티커를 제공하며, API 키가 필요 없는 데이터 소스와 호스트 프록시+캐시를 사용합니다.

Open-Meteo 기반의 DSH 날씨 탭과 날씨에 따라 바뀌는 테마입니다.

DSH Typewriter: WebAudio로 타이핑 분위기음을 재현하며, 플러그인 전용 설정 API를 제공하고 오디오 파일을 전혀 사용하지 않습니다.

재미있게 밈을 검색합니다: 분위기를 설명하면 에이전트가 정말 어울리는 실제 밈을 찾아 전송합니다.

Universal image generation for DeepSeek Harness: auto-discovers image models from any OpenAI-compatible endpoint (SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen and more), with agent tools and REST API.

China A-share financial data MCP server for the harness: 11 fin_data__* tools (quotes/K-lines/financials/calendar/special-data/announcements/EDB/reconcile/funds/indices) over THS free official REST (primary) + AKShare (fallback) + Wind (exclusive domains), with observable degradation, context-budget compression (result-side -72.2% measured), and an offline 10-year market-data lake; BYOK.

Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-t

The pet that grows with your agent: 5 evolution stages earned from real signals (verified rules, completed sessions, tool calls, compactions), agent-state mirroring, and one-click growth share cards. Zero dependencies, 100% local.

Real-time quote bull/bear desk pet for DSH: a portfolio-average-driven pet that runs faster and jumps higher the closer gains reach 20%, with a watchlist panel for searching and adding stocks plus a live "race" of how each holding is moving.

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.

Voice AI girlfriend for the Web UI: FunASR mic input, Qwen3-TTS spoken replies, companion animation window, and two-way QQ chat (text/voice/image push) via NapCat.

Ingestion-time tool-output curation: keeps error and warning lines plus head and tail, spills the full text to disk with a pointer the model can read back; covers every text tool, small results pass through untouched.