DoloresCaritasAngelus/DSH-AUX
Auxiliary model system for DeepSeek Harness: unified aux-LLM routing (per-task model, timeout, concurrency, failure cooldown, main-model fallback) + vision_analyze / web_extract / compress_text tools, settings page, and session image lifecycle cleanup.
正在读取 GitHub README...
README 暂时无法读取。
前往仓库PROJECT TOPICS
VALIDATION LADDER
CLASSIFICATION EVIDENCE
系统优先读取 GitHub Topics，再与站内分类词典和词根规则比对。当前命中：vision。
Anionex
让纯文本模型更好地做视觉任务的DeepSeek Harness插件：带意图的图片问答、长截图 OCR、UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
ysr666
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
cocofhu
DeepSeek Harness 搜番插件：对话内多源搜索番剧，卡片展示 Bangumi 评分与详情，支持复制磁力。