Llamatik 2.0 is here · SDK, Agents, Video, Share this device →

Private AI that lives
on your devices.

Chat, see, listen and create — with models that run on your phone, laptop and browser. No account. No ads. Your prompts never leave your device unless you say so.

Runs locally
Free & open source Works offline No account Android · iOS · Mac · Windows · Linux · Web
llama.cppwhisper.cppstable-diffusion.cppKotlin MultiplatformComposeKtorGGUFMIT licensed
llama.cppwhisper.cppstable-diffusion.cppKotlin MultiplatformComposeKtorGGUFMIT licensed

What it does

More than a chatbot.
A whole AI studio in your pocket.

Text, vision, voice, images, video and documents — each one running on the engine you already trust, on the hardware you already own.

Chat

Fast, streaming conversations

Pick any GGUF model — download from the built-in catalog or load a file from your device. Markdown, code blocks and history included.

Vision new

Show it a picture

Ask about photos, screenshots and documents with on-device vision models like SmolVLM.

Voice

Talk, don't type

Whisper transcribes speech offline — with timestamps, translation to English, and speaker turns.

Video new

Text-to-video, on your hardware

Describe a scene and get a short clip — encoded to H.264, saved to your gallery, with optional on-device upscaling.

Images

Generate art offline

Text-to-image and image-to-image, with live progress and ControlNet guidance for pose, depth and edges.

Agents 2.0

An assistant that acts

Planner, tools, permissions and an audit log — with companion personas from Professional to Pet.

Documents

Chat with your PDFs

Local RAG: chunking, embeddings and MMR retrieval — your files never get uploaded.

Speed

Multi-token prediction

Speculative drafting for models that support it (Qwen3.5, GLM-4) — more tokens per second.

Privacy

Offline by default

Models and chats stay on your device. No account, no ads, optional diagnostics that are off by default, and a clear warning before you ever connect to a server.

Share this device new in 2.0

Every device you own,
one shared brain.

Your gaming PC has the horsepower. Your phone has you. Turn on Share this device and Llamatik serves your loaded models to your other devices over the local network — found automatically with mDNS.

  • Approve each device before it can use yours — no shared secrets to leak.
  • Hands-off discovery. Nearby Llamatik hosts show up on their own.
  • Resilient streaming. Drop off Wi-Fi mid-answer and it reconnects and continues.
  • Android, Desktop and iOS can host. Your battery thanks you.

Connections between devices are currently plain HTTP — keep them on networks you trust.

Llamatik 2.0

The biggest release yet.

The app is the showcase. The engine underneath is now a full Kotlin Multiplatform AI SDK.

SDK

Chat, models, downloads, RAG and the new Assistant facade — UI-free and publishable.

Agents

A Kotlin DSL and an AgentRuntime with permissions, confirmations and audit.

Video

Text-to-video, ControlNet, live progress and video upscaling.

Vision

Multimodal image analysis through libmtmd — SmolVLM and friends.

Network

Connect to servers, discover nodes, and share your own device.

llama.cpp 1.0

Built on the new semantic-versioned releases of llama.cpp and whisper.cpp.

For developers

Build it into your own app.

The same stack that powers the Llamatik app is on Maven Central. One Kotlin API for Android, iOS, Desktop and WASM — no Python, no glue code.

Click a module to copy its Gradle line.

val agent = Agent {
    name("Kotlin Assistant")
    systemPrompt("You are an expert Kotlin developer.")
    temperature(0.7f)
    memory(SlidingWindowMemory(windowSize = 20))
    tools { builtIns() }   // calculator, date/time, uuid, random
}

agent.stream("What is 17% of 2,340?").collect { chunk ->
    when (chunk) {
        is AgentStreamChunk.Delta -> print(chunk.text)
        is AgentStreamChunk.Done  -> println()
        else -> Unit
    }
}
val path = LlamaBridge.getModelPath("phi-2.Q4_0.gguf")

LlamaBridge.updateGenerateParams(
    temperature = 0.7f, maxTokens = 512,
    topP = 0.95f, topK = 40, numThreads = 4,
)
LlamaBridge.initGenerateModel(path)

// Same call on Android, iOS, Desktop and WASM
val answer = LlamaBridge.generate(
    "Explain Kotlin Multiplatform in one sentence."
)
commonMain.dependencies {
    // llama.cpp, whisper.cpp, stable-diffusion.cpp — one Kotlin API
    implementation("com.llamatik:core:<version>")

    // Chat, models, RAG, Agent DSL, Assistant facade
    implementation("com.llamatik:sdk:<version>")

    // AgentRuntime: planner, permissions, audit, workflows
    implementation("com.llamatik:sdk-agent:<version>")
}
llamatik-server — :8080
$ curl -N localhost:8080/v1/generation/stream \
    -H "Content-Type: application/json" \
    -d '{"prompt":"Say hi from my own server"}'

Llamatik Server

Your own inference backend.
Same API. Zero code changes.

Need more power than a phone? Self-host a Ktor server that speaks exactly the same API as the library — text, embeddings, speech, images, video and vision, streamed over SSE.

  • Full LlamaBridge, WhisperBridge, StableDiffusionBridge and MultimodalBridge parity
  • Schema-constrained JSON, KV sessions, speculative decoding, GPU offload
  • JWT auth, profiles, Docker-ready — or embed com.llamatik:server in your own app

Llamatik Code

An AI pair programmer that never sees the cloud.

A privacy-first coding assistant for IntelliJ IDEA, Android Studio and the JetBrains family. Load a GGUF model once and your code never leaves your machine.

  • Ask mode — unlimited chat aware of your files and selection
  • Agent mode — proposes diffs and waits for your approval
  • MCP servers and built-in web docs search, no API key
Llamatik Code inside an IntelliJ-based IDE

Why local-first

Your AI. Your data. Your rules.

01

Private by design

Prompts, documents and voice are processed on your hardware. There is no account to create and no cloud to trust.

02

Works anywhere

On a plane, in a basement, behind a firewall. Once a model is downloaded, the network is optional.

03

Open source

MIT-licensed and built in the open. Inspect it, fork it, ship it. A 2026 Kotlin Foundation Grant winner.

What users say

Kind words from Google Play.

“INCROYABLE !!!! MERCI AU DÉVELOPPEUR🤩 cette application gratuit illimitée sans soucis sans pub marche en hors ligne merci beaucoup je mettrai 10 étoiles si je pouvais”

Paul · Google Play review

“muito bom, cumpre oque promete! … Mas o app cumpre exatamente oque diz você consegue ter acesso a ia sem Internet.”

Jean C. · Google Play review

“love it, just like the library <3 thanks for your work”

Jonáš B. · Google Play review

“superb local integration functions on Oppo android device.”

Harold L. · Google Play review

Excerpts from public Google Play reviews, shown in the language they were written in and with first names only. They are a selection of the most positive ones; the full, unfiltered list is on the store page.

Compared

How Llamatik compares.

An honest look at Llamatik next to the tools people usually consider. Cloud models are more powerful; Llamatik trades some raw power for privacy, offline use and ownership.

FeatureLlamatikOllamaLM Studiollama.appChatGPTClaude
Runs entirely on your deviceYesYesYesYesNoNo
Works offlineYesYesYesYesNoNo
Native Android and iOS appsYesNoNoNoYesYes
Runs the model inside a browser tabYesNoNoNoNoNo
Vision, voice and image generation on deviceYesPartlyPartlyPartlyNoNo
Open sourceYesYesPartlyYesNoNo
Embeddable Kotlin Multiplatform SDKYesNoNoNoNoNo
Share one device's models with your other devicesYesPartlyPartlyNoNoNo
No account requiredYesYesYesYesPartlyNo
Free to useYesYesYesYesPartlyPartly
Frontier-scale model qualityNoPartlyPartlyPartlyYesYes

Based on public information as of November 2026. Products change quickly: if something is out of date, tell us at info@llamatik.com and we will fix it.

Ready to run AI your way?

Ask your first question in seconds — no sign-up.