NovelClaw — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 HITSZ-DS · Agent Tool · ★ 146

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

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

About NovelClaw

NovelClaw ✨ A structured long-form fiction workspace centered on chapter drafting, inspectable runs, manuscript review, and memory-aware writing control. 💡 NovelClaw is not a one-shot prompt wrapper. It turns long-form fiction work into an inspectable writing workspace with sessions, storyboards, manuscript surfaces, character and world views, and editable memory banks. 🌐 Try it online: colong-idea-studio.cloud 🚀 Start locally now: .\STARTLOCAL.bat <img

agentaicreative-writingcreative-writing-aifastapillmmulti-agentnovelopenclawrag

Quick Facts

Stars146
Forks18
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score65.8010108248936/100
Last Updated2026-03-29
Created2026-03-07
Platformsbrowser, python
Est. Tokens~3623k

Compatible Skills

These tools work well together with NovelClaw for enhanced workflows:

  • slop-guard — semantic(0.31)+complementary+rare_topics+same_lang+similar_pop+shared_platform (65%)
  • academic-paper-skills — semantic(0.33)+complementary+same_lang+similar_pop+shared_platform (57%)
  • anti-slop-writing — semantic(0.39)+complementary+rare_topics+similar_pop+shared_platform (53%)
  • ai-collab-playbook — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (51%)

NovelClaw alternative? Top 6 similar tools

Looking for a NovelClaw alternative? If you're comparing NovelClaw 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.

  • NovelClaw by iLearn-Lab · ⭐ 374

    Dynamic-memory-first collaborative AI framework for long-form story generation, chapter planning, and coherent

  • aser by AmeNetwork · ⭐ 472

    Aser is a lightweight, self-assembling AI Agent frame.

  • character-arc by uu201 · ⭐ 568

    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

  • oreilly-ai-agents by sinanuozdemir · ⭐ 299

    An introduction to the world of AI Agents

  • context-compressor by Huzaifa785 · ⭐ 90

    AI-powered text compression library for RAG systems and API calls. Reduce token usage by up to 50-60% while pr

  • scrivener-mcp by writerslogic · ⭐ 61

    The definitive MCP server for Scrivener — connect your novels, screenplays, and manuscripts to Claude, ChatGPT

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is NovelClaw?

NovelClaw is Dynamic-memory-first collaborative AI framework for long-form story generation, chapter planning, and coherent narrative writing. It is categorized as a Agent Tool with 146 GitHub stars.

What programming language is NovelClaw written in?

NovelClaw is primarily written in Python. It covers topics such as agent, ai, creative-writing.

How do I install or use NovelClaw?

You can find installation instructions and usage details in the NovelClaw GitHub repository at github.com/HITSZ-DS/NovelClaw. The project has 146 stars and 18 forks, indicating an active community.

What license does NovelClaw use?

NovelClaw is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to NovelClaw?

The top alternatives to NovelClaw on Agent Skills Hub include NovelClaw, aser, 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