rag

白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。

蒸留蔵 — distilled long-term memory for agents: recall by meaning, writing gated by evidence, one kura per agent mode. Ships as a DeepSeek Harness plugin and an MCP server.

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

让 DeepSeek Harness 拥有跨会话长期记忆：AI 自动记住你是谁、你的项目和偏好，新会话直接带上背景，生活与工作记忆自动分开互不干扰，零配置无感运行 | Long-term memory for DeepSeek Harness: the AI remembers who you are, your projects and preferences across sessions, keeps personal and work memories separate, zero-config.

Installable DeepSeek Harness knowledge base plugin

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_diagnose — SQLite-backed index via the storage domain, local embedding, zero model downloads.

本地优先的文献知识库 RAG(DeepSeek Harness 插件):混合检索正文与图注,把模糊记忆定位到具体段落与图表,DOI 一键直达原文。Local-first literature RAG for DSH — turn a fuzzy memory into an exact passage/figure, one-click DOI to source.

Fully local document intelligence for DeepSeek Harness. Parse PDF, Office files, images, and scanned documents with offline OCR. | DeepSeek Harness 全本地文档智能插件，支持 PDF、Office、图片与离线 OCR

DeepSeek Harness 长期记忆插件：四通道检索融合 + 记忆演化闭环，记忆构建与检索方法来自 ICLR 2026 论文 MemGAS。Long-term memory plugin for DeepSeek Harness (dsh).

Local knowledge base for DeepSeek Harness: zero-dependency SQLite FTS5 index for markdown/text/code/web pages, source-cited retrieval, session experience library, interactive kbquery Web panel + knowledge galaxy.

Source-grounded deep research, writing, and learning plugin for DeepSeek Harness (dsh): steerable checkpoints, mid-run steering, and citations verified against retrieved sources.

Turn DeepSeek Harness into a self-hosted enterprise Agent platform with knowledge, research, content generation, governance, and admin controls.

DeepSeek Harness 主体长期记忆插件：语义召回、实体图谱、状态卡、presets、可配置嵌入；任务看板已独立为 dsh-livetaskboard。

DeepSeek Harness cross-session long-term memory + user profile plugin: the AI remembers who you are, your projects and preferences across sessions. Pure Markdown, zero-config, fully local. (monorepo: dsh-memory-core + dsh-memory-ui)

Learning assistant extension for DeepSeek Harness (dsh): brings DeepTutor tutoring to your agent — deep explanations, self-test questions, learning paths, personal knowledge-base search (RAG), and note archiving. | 面向 DeepSeek Harness 的学习辅助扩展:为 agent 接入 DeepTutor 辅导能力 —— 深度讲解、自测题、学习路径规划、个人知识库检索(RAG)与笔记归档。

Memory and token-optimization plugin toolkit for DeepSeek Harness: cross-session knowledge graph memory + five-layer token-saving orchestration.

ARPM-derived local hybrid RAG plugin for DeepSeek Harness

The deny-by-default governance kernel for AI agents — permissions, L0–L4 guardrails, human approvals and an immutable audit chain as an Apache-2.0, framework-neutral library. Gate LangGraph / CrewAI / n8n / Dify or plain scripts in three lines.

Living memory for DeepSeek Harness — self-tending knowledge base: nightly patrol, temporal decay, RRF hybrid recall, knowledge graph. Built by 暖暖 (NuanNuan).

VERITAS - a research engine that can't cite something a source never said. Mechanically-verified citations (phantom rate 0% by construction), Independent Corroboration Score that exposes syndication laundering, and a compounding evidence graph. DeepSeek Harness plugin + standalone CLI. Zero dependencies.

DeepSeek Harness 本地 RAG 知识库插件：本地文档切片、向量化、语义检索，全程本地运行（Ollama + 纯前端/主机端）。A local-first RAG knowledge base plugin for DeepSeek Harness.

A local knowledge pulgin for DeepSeek Harness

Event-based long-term memory for LLM agents — associative surfacing over query RAG. Closed-loop episodic events, budgeted injection, tiered forgetting. Claude Code hooks + DeepSeek Harness plugin, one shared .memory/ format.

Memory retrieval plugin for DeepSeek Harness (dsh): wiki double-link memory graph with 9 tools — hybrid search, read, link-scan, remember, forget, compile, health-check, resident retriever subagent

Local-first RAG knowledge tools for DSH: kb_query / kb_ingest / kb_crawl / kb_related, backed by the kb-rag Python pipeline (Ollama bge-m3 + ChromaDB). Zero API cost, on-premises.

该仓库暂未提供项目说明。

DeepSeek Harness plugin: multi-tier memory management, semantic retrieval, structured memory, and model-context awareness for infinite context.

中文 DSH 知识复习插件：有证据才回答、资料缺失提醒补充学习视频。

该仓库暂未提供项目说明。

Workspace-scoped, local-first LLM wiki plugin for DeepSeek Harness.

Local knowledge base RAG for DeepSeek Harness

该仓库暂未提供项目说明。

Turn local files into versioned evidence in DeepSeek Harness: composer upload, private local retrieval, and coordinate-exact PDF/DOCX/XLSX/PPTX reads.

Local document RAG retrieval MCP server for DeepSeek Harness — agents search your local .md/.txt docs with source citations. 100% local (fastembed + Chroma), no API keys.

Evidence-linked passive long-term memory for DeepSeek Harness · 让长期记忆自然涌现