899 results
Cross-session memory cue bank for DeepSeek Harness: builds a persistent event-cue library (keywords, user language idiosyncrasies) and re-activates remembered event details on topic switches, mirroring human episodic recall.
Markdown folder long-term memory for DeepSeek Harness: one file per fact, an index line per memory, mounted into every request as a system prompt section
Forgetting engine for AI agents — memory TTL, decay, eviction, audit. The opposite of memory programming.
Pure-incremental directive-driven compaction for DeepSeek Harness: /compact-directive <requirement> summarizes the session middle per your requirement, /trim-directive <requirement> trims the whole conversation per your requirement
Let text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.
AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.
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.
把 git 状态与仓库规范动态注入 system prompt：分支/脏文件数/最近提交 + 仓库规范指引（官方 system-prompt section/context/variable 缝隙插件）
DeepSeek Harness bundle: inject the user's IDE context (open editors + current selection) into each turn, via the Claude Code IDE WebSocket bridge (IntelliJ IDEA & VS Code).
Visual percentage and token settings for official DeepSeek Harness compaction
DSH conversation annotator: select transcript text, attach a note in a popup, then send the compiled quote+note pair through the composer.
DSH plugin: context archiving + historical retrieval — archive_session / search_archive tools over the session-archive skill (zstd session-log decode).
DeepSeek Harness (dsh) bundle plugin: vision_analyze tool lets text-only LLM agents read images via SenseNova VLM, with Schemastery config and single-source credentials
DSH web plugin: provider quota/balance badges — composer chip beside the context meter plus per-row badges on the Models settings page (GLM/Kimi/OpenCode/DeepSeek/Moonshot/xAI + Sub2API gateway auto-detect)
A paper-review panel for the DeepSeek Harness: converts PDF papers into structured, selectable text (columns, headings, tables, sub/superscripts, table of contents) with figure and display-equation rendering, a floating ask-about-the-selection dialog, and per-project paper stores under a Paper workspace.
SimpleTex 专用 OCR/公式识别工具 simpletex_recognize：task=formula 返回 LaTeX（含置信度），task=text 返回 Markdown，task=auto 按问题关键词路由。GUI 设置卡热配置 token/端点/上限。
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.
通用项目 AI 文档协议 skill：每项目一份 docs/.ai 认知库，防上下文涣散、保项目认知精细。（DSH plugin）
字符串工具：大小写/驼峰/蛇形/短横线/slug 转换与文本统计（字符/词/行/字节）
Reusable trajectory-tree context, exact-turn forks, and bounded cross-session recall for DeepSeek Harness
提供多种文本转换功能的MCP服务器，包括大小写转换、反转字符串、检测回文等功能。
Zero-loss tool-result pruning for the DeepSeek Harness (DSH): oversized tool results are spilled to a file first, then pruned with exact elided-span offsets and a recovery locator. A dsh-plugin.
Agent instruction manager for DeepSeek Harness: edit, refine, and template the AGENTS.md files the harness actually reads — the user-global ~/.dsh/AGENTS.md and per-workspace AGENTS.md — from a sidebar panel.
一个功能完整的星座 MCP (Model Context Protocol) 服务，提供星座信息查询、运势分析、配对测试等功能。