Skip to content
View Siddhesh2377's full-sized avatar
🪨
Eating Stones
🪨
Eating Stones
115 followers · 11 following

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex3Achievement: Public SponsorAchievement: Starstruckx2Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex3Achievement: Public SponsorAchievement: Starstruckx2Achievement: QuickdrawAchievement: YOLO

Block or report Siddhesh2377

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Siddhesh2377/README.md

Siddhesh Sonar

Profile views

On-device AI at RunAnywhere (YC W26). C++ core, thin bridges to Kotlin, Swift, Flutter, and React Native.

Lately that is Wally, the CLI that runs open models on your machine, and local decision models in the SDK through llama.cpp and MLX.

Projects

ToolNeuron. Offline Android AI. Chat, images, and speech stay on the device.

Ai-Systems-New. The C++ SDK behind ToolNeuron. llama.cpp for chat, QNN and MNN for images, ONNX Runtime for speech.

llama.cpp-android. CPU-only llama.cpp for Android, with ARM kernels and big.LITTLE scheduling.

ForgeAI. Desktop app to load, inspect, and merge model files. Rust and Tauri.

I also wrote Hexagon DSP kernels that skip the QNN SDK. The benchmark reported 8 TFLOPS. The matrix unit was fused off. Writeup.

C++ llama.cpp GGML Android Kotlin Swift MLX Hexagon Rust

Mumbai · Blog · Email · LinkedIn

Pinned Loading

  1. ToolNeuron ToolNeuron Public

    Encrypted & Privacy First, On Android Device AI App

    Kotlin 473 62

  2. RunanywhereAI/wally RunanywhereAI/wally Public

    Get up and running with GLM-5.3-flash, DeepSeek, Gemma and other open source frontier models.

    Rust 1.6k 93

  3. RunanywhereAI/runanywhere-sdks RunanywhereAI/runanywhere-sdks Public

    Production ready toolkit to run AI locally

    C++ 10.3k 388

  4. Ai-Systems-New Ai-Systems-New Public

    On-device AI SDK powering ToolNeuron — LLM chat & tool calling (llama.cpp), Stable Diffusion image generation (QNN/MNN), image processing (upscale, segment, inpaint, depth, style), and TTS. Native …

    C++ 33 7

  5. ForgeAi ForgeAi Public

    ForgeAI : Your local model workshop, Load. Inspect. Merge. Ship.

    Rust 16 2

  6. llama.cpp-android llama.cpp-android Public

    Custom llama.cpp fork with character intelligence engine: control vectors, attention bias, head rescaling, attention temperature, fast weight memory

    C++ 11 7