LeanType — security grade SAFE, quality 59/100

Security audit verdict: SAFE · quality 59/100

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 LeanBitLab · Agent Tool · ★ 1.0k

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

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

About LeanType

LeanType LeanType is a fork of HeliBoard - a privacy-conscious and customizable open-source keyboard based on AOSP/OpenBoard. This fork adds optional AI-powered features using Gemini, Groq, and OpenAI-compatible APIs, offering a hybrid experience: a private, offline core with opt-in cloud intelligence. What's New in LeanType 🤖 Multi-Provider AI - Proofread using Gemini, Groq (Llama 3, Mixtral), or OpenAI-compatible providers. Supports dynamic fetching of latest models directly from providers. 🛡️ Offline AI - Private, on-device proofreading and translation using ONNX models (Offline build only). 🌐 AI Translation - Translate selected text directly using your chosen AI provider, with a separate model selector. [🧠 Custom AI Keys

ai-toolsandroidaospcustomisationfree-softwaregemini-apigguf-modelsgroqkeyboardkotlin

Quick Facts

Stars1,049
Forks62
LanguageKotlin
CategoryAgent Tool
LicenseGPL-3.0
Quality Score59.313591499027/100
Open Issues52
Last Updated2026-10-13
Created2026-01-15
Platformsgemini
Est. Tokens~18k

LeanType alternative? Top 6 similar tools

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

  • ToolNeuron by Siddhesh2377 · ⭐ 473

    On-device AI for Android — LLM chat (GGUF/llama.cpp), vision models (VLM), image generation (Stable Diffusion)

  • OGAM by off-grid-ai · ⭐ 3.2k

    The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vi

  • awesome-startup by KrishMunot · ⭐ 2.3k

    :sunglasses: All the required resources to build your own startup

  • webbrain by webbrain-one · ⭐ 1.4k

    Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

  • PixelBoard by Akshayykadam · ⭐ 719

    Unlock Google 11's Gemini "Rambler" Natural Voice Dictation & AI Writing Tools on ANY Android phone. No root r

  • ctxport by nicepkg · ⭐ 644

    Copy AI conversations as clean Markdown Context Bundles — one click from ChatGPT, Claude, Gemini, DeepSeek, Gr

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Kotlin Agent Tools

Frequently Asked Questions

What is LeanType?

LeanType is LeanType is an Open-source keyboard, fork of HeliBoard with additional features and customisation. It is categorized as a Agent Tool with 1.0k GitHub stars.

What programming language is LeanType written in?

LeanType is primarily written in Kotlin. It covers topics such as ai-tools, android, aosp.

How do I install or use LeanType?

You can find installation instructions and usage details in the LeanType GitHub repository at github.com/LeanBitLab/LeanType. The project has 1.0k stars and 62 forks, indicating an active community.

What license does LeanType use?

LeanType is released under the GPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to LeanType?

The top alternatives to LeanType on Agent Skills Hub include ToolNeuron, OGAM, awesome-startup. 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