Knowledge base & RAG plugin for DeepSeek Harness (DSH): chunking, local embeddings, hybrid search, management panel

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

Local document knowledge base for DeepSeek Harness: library_add/remove/list, hybrid semantic+keyword library_search with diversity re-ranking, relevance filtering and lost-in-the-middle avoidance, citation-aware injection, library_cite_check and library_d

Evidence-first reading for AI agents — turn articles, books and PDFs into traceable claims, evidence, source locations and knowledge maps.

给 AI agent 用的长期记忆：记住的东西存成普通 markdown 文件，有大小上限的索引每次会话自动读入。支持 Claude Code、Codex、OpenClaw、Kiro 等，DeepSeek Harness（dsh）有专用插件 dsh-engramory。

DSH RedTeam 模式：一句话拉起红队作战智能体（资产测绘 / 攻击链 / 得分目标 / 报告 / POC 知识库），含六个角色、23 个原生技能、常驻右侧控制台与一键自动更新

DSH plugin development as an on-demand agent skill: official docs mirror, version-compatibility matrix, migration seams, measured pitfalls, plus a scaffolder, checker and pack verifier CLI.

Session Workbench for DeepSeek Harness: session-library full-text search + recall + conversation-view management (show/hide + reorder). 会话工作台：会话库（历史会话全文搜索与召回）+ 会话视图（标签栏显示/隐藏 + 拖拽排序）。

AI-native engineering environment management that makes your codebase agent-ready.

Multi-agent mathematical problem-solving & verification frameworks for DeepSeek Harness — FOUR agent presets in one install: vibe-math-v2 (probability-driven, classic: qs.json + Propos knowledge base + explorer→solver→review/debate verdict), vibe-math-v3

Third-party provider reasoning-effort AND input-modality settings for DeepSeek Harness: thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models