ToolNeuron — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

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 Siddhesh2377 · LLM Plugin · ★ 461

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

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

About ToolNeuron

ToolNeuron On-device AI for Android. No Google Play services, no telemetry, no cloud. Models, chats, RAG documents, and key material stay on the phone. The point isn't to clone ChatGPT into your pocket. It's to give you a chat surface, a RAG pipeline, a voice loop, and a plugin runtime that all run with the radio off if you want them to. Play Store · Repo · Releases · Issues · Discord What it does Chat against any compatible GGUF model. Streaming output, multi-turn, optional thinking mode, per-turn tok/s + TTFT + peak-memory metrics. Vision via colocated projector files. Image bytes cross AIDL as PFDs, never . RAG over PDF, DOCX, XLSX, PPTX, ODT, EPUB, RTF, MD, HTML, JSON, XML, CSV, TXT. Source bytes are content-addressed; re-attach a doc to any chat from the picker. Voice through sherpa-onnx. Streaming TTS that chunks by sentence, tap-to-toggle STT. VITS / Piper / Whisper all work. HTTP server in its own process. OpenAI-shaped endpoints, bearer-token auth, rate limit, audit log. Material 3 web UI bundled at . HuggingFace browse — full-screen explorer with the filters that matter (pipeline tag, library, p

ai-personasandroidgguf-modelsjetpack-composekotlinllama-cppllmlocal-aimobile-aion-device-ai

Quick Facts

Stars461
Forks59
LanguageKotlin
CategoryLLM Plugin
LicenseMIT
Quality Score69.9651342357576/100
Open Issues22
Last Updated2026-05-18
Created2025-05-29
Est. Tokens~77984k

ToolNeuron alternative? Top 6 similar tools

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

  • compose-skill by aldefy · ⭐ 561

    Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W

  • compose-skill by Meet-Miyani · ⭐ 300

    Compose Skill (Compose Kit): agent skills for Jetpack Compose & Compose Multiplatform. Makes Claude Code, Code

  • guaardvark by guaardvark · ⭐ 244

    The self-hosted AI studio: local video, image, music, voice, LoRA training, coding swarms, RAG and screen agen

  • agentic-signal by code-forge-temple · ⭐ 177

    🤖 Visual AI agent workflow automation platform with local LLM integration - build intelligent workflows using

  • roampal by roampal-ai · ⭐ 125

    Memory that learns what works.

  • forge by antoinezambelli · ⭐ 2.2k

    A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows

More LLM Plugin Tools

Explore other popular llm plugin tools:

View all LLM Plugin tools →

Popular Kotlin Agent Tools

Frequently Asked Questions

What is ToolNeuron?

ToolNeuron is On-device AI for Android — LLM chat (GGUF/llama.cpp), vision models (VLM), image generation (Stable Diffusion), tool calling, AI personas, RAG knowledge packs, TTS/STT. Fully offline, zero subscriptio. It is categorized as a LLM Plugin with 461 GitHub stars.

What programming language is ToolNeuron written in?

ToolNeuron is primarily written in Kotlin. It covers topics such as ai-personas, android, gguf-models.

How do I install or use ToolNeuron?

You can find installation instructions and usage details in the ToolNeuron GitHub repository at github.com/Siddhesh2377/ToolNeuron. The project has 461 stars and 59 forks, indicating an active community.

What license does ToolNeuron use?

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

What are the best alternatives to ToolNeuron?

The top alternatives to ToolNeuron on Agent Skills Hub include compose-skill, compose-skill, guaardvark. 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 LLM Plugin tools