@deepseek-ai/dsh-memory-connect
Cross-session memory plugin for DSH — auto-extraction, semantic recall, scheduled maintenance, LLM-powered consolidation, context explosion prevention, global Soul identity
74 results
Cross-session memory plugin for DSH — auto-extraction, semantic recall, scheduled maintenance, LLM-powered consolidation, context explosion prevention, global Soul identity
面向中文读者的英文论文精读 Agent 预设插件:自动安装 paper-tutor 预设,提供零依赖 PDF 文本/图表提取(pdf_extract)、工作区论文盘点(paper_scan)、LaTeX 结构解析(tex_structure)与图表视觉分析(paper_figure),结合论文代码溯源讲解论文。
文档文字识别。用户提供 PDF/扫描件/图片(合同、发票、书页、截图),需要提取文字、转成可编辑文本时使用。扫描件自动 OCR(macOS Vision,中英文)。Document OCR: extract editable text from PDFs, scans, and images (contracts, invoices, book pages, screenshots) via macOS Vision.
Convert PDF and Word (DOCX) documents to clean Markdown. Use when the user asks to convert PDF/Word to Markdown, extract document text/structure, 提取 PDF/Word 内容, 转 Markdown, or prepare documents for editing/RAG. Handles Chinese documents and Windows paths well.
DeepSeek Harness skill bundle: function-extraction (loads SKILL.md).
Dual-face (host + client) plugin: independent text-output ocr_image tool + tools/execute read_image capability dispatch + ctx.ocr seam, with a conversation.input.left OCR toggle button.
TODO/FIXME 提取
视频转文字。用户发抖音分享链接(获取标题/作者/点赞等元数据),或本地视频文件(语音转写全文)时使用。抖音链接用 SSR 解析无需 Cookie。Video to text: extract metadata from Douyin share links, or transcribe speech from local video files.
Cross-session self-learning memory for DeepSeek Harness, ported from XT-AGENT packages/memory. BM25 relevance injection + background extraction (sanitize/dedupe/merge) + lifecycle archive + memory_read/memory_search/memory_write tools.
为AI开发和QA设计的模型上下文协议服务器,提供AntV文档上下文和代码示例。
Overlay reader for agent output files: Markdown/GFM rendering, in-panel PDF preview, DOCX/XLSX/PPTX text extraction, reply-end file chips. Pure JS, zero dependencies, no persistent UI.
怀疑驱动开发:每个非平凡决策在落地前接受新鲜上下文的对抗性审查(CLAIM→EXTRACT→DOUBT→RECONCILE→STOP)。受 addyosmani/agent-skills(88k★ MIT)启发。
Model-facing describe_image + extract_text tools for the DeepSeek Harness web GUI: gives a text-only model reliable image understanding and OCR through an OpenAI-compatible vision endpoint, with critical-inspection prompts, auto-preprocessing, retries, and a persistent answer cache.
Memory Tree bridge for DeepSeek Harness — search/persist memory, manage the memory tree, and drive the local/cloud extraction backends. · 记忆树桥接:检索/落盘记忆、管理记忆树、本地/云端提取开关。
DSH 自动解压工具:魔数识别真格式(不信伪装后缀)、递归解压嵌套压缩包、多密码池自动尝试、SFX/分卷配对、私有格式归类报告。核心基于 7-Zip。
MCP服务器提供从本地文件、URL提取图像并转换为base64格式的功能,适用于LLM分析。
DSH single-instance multi-tenancy: proxy-identity extraction, session-level owner/access ACL over a sidecar store, shadow exact-routes gating session RPCs, and an event-frame filter hook for the client-connection patch.
Office Word documents for DeepSeek Harness: generate / edit / extract / convert .docx with a pure-stdlib toolkit
Frosted-glass skin for the DeepSeek Harness web UI: pick any image as background, theme colors extracted from it, glassmorphism surfaces.
arXiv paper tools for DeepSeek Harness: search, summarize, translate, and survey papers as native tools. No Python, no MCP — HTML-first extraction.
关键词提取
Enhanced line-selection copy tool for DeepSeek Harness.
Playwright browser automation tools for DSH: open pages, click, type, fill, extract, screenshot.
xmap Excel schema-map tools for DeepSeek Harness — peek/extract/verify/aggregate large Excel sheets with a reusable column-mapping spec library. 模型只写一份几百字节的列映射 spec,引擎用 Excel COM 在模型上下文之外把整张表读成 JSONL。