semantic-search 13

小说写作助手插件（19 个工具）：覆盖「动笔前取材料 → 写完量化自检 → 改稿按优先级复测 → 跨章结构体检」整条流程。含句式模式分析、情感量化与氛围光谱、风格画像报告、文笔六维基线带、本地语义检索（离线）、章节库浏览与摘要、设定表与伏笔登记、原创模式创作资料、连贯性审计（衔接/OOC/大纲对照）、开写包与改稿台；必用词表支持书级+全局两层登记、批量导入、开写包硬清单注入与成稿用词审计；用语规范按作品文化基准（欧式/中式/现代）自动选表，并支持逐词静音。界面为官方侧栏面板（右侧栏标签 + 页脚入口）。附

Conversation history recall for DeepSeek Harness: search the original text of every session (like searching chat records) — literal/fuzzy/semantic retrieval, fully local & offline, plus a silent host auto-recall layer that injects relevant history when yo

Tool search & slimming for DeepSeek Harness: Hermes-style progressive disclosure — search, describe, and call long-tail tools on demand while keeping core tools eager

Persistent memory for DeepSeek Harness: per-conversation notes, selective injection, project memory, semantic Vault search (bge-m3, free optional key) and automatic retrieval — agents stop forgetting.

Requirement-driven dsh plugin discovery and environment recipes ('点菜, not 逛超市' / 插件界的 dotfiles): plugin_guide matches natural-language needs to a curated directory with a scored match breakdown and category/tag filters plus per-category diversity; recipe

Model-facing library_search tool: free cross-ecosystem (npm/crates.io/Maven/Go/PyPI/RubyGems + GitHub) 'has this already been built?' search — exact-name ranked, stars/downloads as fitness signals, no API key required

DeepSeek Harness 插件：一键 API Key 接入法律之星 MCP（语义检索/法条调取/法规列表/批量识别/幻觉校验/批量引用） / One-click API Key connect to LawStar legal-data MCP for DeepSeek Harness

Semantic find tool for the pi coding agent and the DeepSeek Harness — a cascade-search port of jegrep / oh-my-pi jfind

Fold the DSH skill catalog prompt surface: static KV-cache-stable catalog + BM25/bge-m3 hybrid skill_search + autoRoute hints. Rendering-only fold: source.entries stay untouched, the skill tool and /name injection stay host-owned. v0.3.0 adds a semantic r

Fold the DSH tool surface per request + ChainGuard firewall (high-risk block + exfil-chain detection + anti-obfuscation) + BM25/bge-m3 hybrid tools_search. Shrinks schema tokens 80-90% while keeping selection accuracy. v0.2.0 adds a semantic retrieval leg

Persistent, searchable, per-project memory for the DeepSeek Harness: decisions, rules, and sprint context in a queryable DuckDB file, rules enforced on every model request, with a full management UI in the Web Client

DSH plugin: auto-supplement QMD semantic search when the model greps/globs a knowledge-base directory

colgrep — semantic code search (ColBERT multi-vector) for DeepSeek Harness. Adds a `colgrep` tool that finds code by meaning, not exact text.