denova — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by alfredxw · Agent Tool · ★ 706

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is denova safe to install? View the security audit →

About denova

Nova 是面向创作者的 AI-native 创作工作台:用写作模式管理小说创作,用游戏模式运行互动文字冒险,并把资料库、方案预设、上下文、版本与自动化留在同一个可持续迭代的 workspace 里 English | 中文 当前版本:v0.1.17(2026-06-27) · Beta 查看更多界面截图 游戏模式工作台 剧情分支 资料库 方案预设配置 为什么选择 Nova Nova 不是“输入提示词,生成一段正文”的一次性工具,而是为长期创作和互动娱乐准备的完整工作台。它把作品文件、Markdown 编辑、多 Tab、全局搜索、章节统计、结构化资料库、互动故事、Agent 工具调用和本地版本管理放在同一个 workspace 里,让小说创作和互动推进都能基于同一套长期资产持续迭代。 除了写自己的原创故事,Nova 也支持导入既有小说作为同人或改编起点,支持导入 AI 酒馆角色卡来快速建立互动预设。模型可见上下文会按来源和上限渐进式组织,资料库、文件片段、工具结果和历史展示彼此分离,避免把完整历史或全部设定无脑塞进下一轮模型输入。 写作模式

agentai-agentsai-toolsidenovel

Quick Facts

Stars706
Forks118
LanguageGo
CategoryAgent Tool
LicenseApache-2.0
Quality Score63.8969176553559/100
Open Issues5
Last Updated2026-09-10
Created2026-05-19
Platformsgo
Est. Tokens~17k

Compatible Skills

These tools work well together with denova for enhanced workflows:

  • goskills — semantic(0.15)+complementary+same_lang+similar_pop+shared_platform (55%)
  • NovelClaw — semantic(0.34)+complementary+rare_topics+similar_pop (51%)
  • oh-story-claudecode — semantic(0.46)+complementary+similar_pop (51%)
  • tianming-skill — semantic(0.39)+complementary+similar_pop (49%)
  • long-novel-writer — semantic(0.38)+complementary+similar_pop (48%)

denova alternative? Top 6 similar tools

Looking for a denova alternative? If you're comparing denova with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • OpenFic by syrizelink · ⭐ 1.0k

    专为小说创作打造的跨平台、用户友好、AI Native 的一站式 Vibe Wrting 工具。A cross-platform, user-friendly, AI-native, all-in-one Vibe Wr

  • octocode-mcp by bgauryy · ⭐ 838

    MCP server for semantic code research and context generation on real-time using LLM patterns | Search naturall

  • character-arc by uu201 · ⭐ 557

    CharacterArc(弧光) AI 小说创作应用,集项目设定、角色关系、剧情大纲、章节写作与多模型 AI 协作于一体

  • ainovel-cli by voocel · ⭐ 2.0k

    ✨多agent实现全自动AI小说生成

  • agents by inkeep · ⭐ 1.4k

    Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistant

  • cheatengine-mcp-bridge by miscusi-peek · ⭐ 1.2k

    Connect Cursor, Copilot & Claude AI directly to Cheat Engine via MCP. Automate reverse engineering, pointer sc

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Go Agent Tools

Frequently Asked Questions

What is denova?

denova is An AI creative platform for novel writing and AI generated RPG, with built-in support for AI agents, Skills, subagent workflows, automations, image generation, and version control. 一个面向小说创作与 AI 角色扮演游戏. It is categorized as a Agent Tool with 706 GitHub stars.

What programming language is denova written in?

denova is primarily written in Go. It covers topics such as agent, ai-agents, ai-tools.

How do I install or use denova?

You can find installation instructions and usage details in the denova GitHub repository at github.com/alfredxw/denova. The project has 706 stars and 118 forks, indicating an active community.

What license does denova use?

denova is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to denova?

The top alternatives to denova on Agent Skills Hub include OpenFic, octocode-mcp, character-arc. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools