Linghun — security grade SAFE, quality 60/100

Security audit verdict: SAFE · quality 60/100

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 linghungegeg · Agent Tool · ★ 428

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

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

About Linghun

Linghun 本地优先、证据优先的 AI 编程终端 把大模型接到真实项目、真实工具、真实权限、真实验证和真实上下文里。 English README · 中文白皮书 · English Whitepaper · 更新记录 · English Updates · App Bridge Linghun 可以理解成:给大模型装上一套工程化外骨骼。模型负责理解、推理和生成;Linghun 负责把模型接到真实项目、真实工具、真实权限、真实验证和真实上下文里。 普通聊天工具可以回答“应该怎么改”。Linghun 更关心另一件事:它有没有真的读过相关代码、有没有真的改对文件、有没有真的跑过验证、有没有把不确定的地方说清楚。 这就是 Linghun 反幻觉系统的价值:不是让模型少说错话那么简单,而是把“读事实、看证据、区分验证范围、拒绝空口完成、说明不确定性”变成运行时约束。模型仍然会推理和生成,但关键工程结论不能只靠模型自信。 Novita x Harbor 榜单记录 Linghun 已完成 Novita x Harbor Agent Benchmark 四个公开 TB2.1 榜单的运行与提交: [f77879ac-b30f-47bb-8fb1-650108364fc0](https://hub.harborframework.com/jobs/f77879

agent-runtimeagiaiai-agentai-codingcapability-runtimecoding-agentdeveloper-toolsevidenceevidence-first

Quick Facts

Stars428
Forks30
LanguageTypeScript
CategoryAgent Tool
LicenseApache-2.0
Quality Score59.707279304499/100
Last Updated2026-08-19
Created2026-05-14
Platformsnode
Est. Tokens~19k

Linghun alternative? Top 6 similar tools

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

  • open-multi-agent-kit by dmae97 · ⭐ 122

    Evidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents. Routes tasks into scoped DAG

  • claude-code-open by kill136 · ⭐ 158

    Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.

  • Overture by SixHq · ⭐ 641

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • smart-ralph by tzachbon · ⭐ 544

    Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured

  • clawless by open-gitagent · ⭐ 525

    ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers

  • golembot by 0xranx · ⭐ 322

    Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Disco

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is Linghun?

Linghun is AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.. It is categorized as a Agent Tool with 428 GitHub stars.

What programming language is Linghun written in?

Linghun is primarily written in TypeScript. It covers topics such as agent-runtime, agi, ai.

How do I install or use Linghun?

You can find installation instructions and usage details in the Linghun GitHub repository at github.com/linghungegeg/Linghun. The project has 428 stars and 30 forks, indicating an active community.

What license does Linghun use?

Linghun 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 Linghun?

The top alternatives to Linghun on Agent Skills Hub include open-multi-agent-kit, claude-code-open, Overture. 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