Projects sharing features with Pocketpal Ai

MNN is a high-performance inference engine and framework designed for on-device machine learning. It provides a comprehensive environment for executing, optimizing, and deploying neural network models directly on mobile and resource-constrained edge devices. The framework distinguishes itself through a robust model optimization toolkit that supports quantization, compression, and structural graph manipulation to minimize memory footprint and maximize execution speed. It features a modular architecture that abstracts hardware-specific backends, allowing models to run efficiently across diverse

ExecuTorch is a lightweight C++ runtime for deploying PyTorch models on mobile, embedded, and edge hardware. It provides an ahead-of-time compilation pipeline that exports, quantizes, and lowers model graphs into compact serialized programs, then executes them through a minimal runtime with hardware acceleration and on-device large language model inference capabilities. The project distinguishes itself through a hardware accelerator delegate system that partitions model subgraphs and offloads computation to specialized backends including NPUs, GPUs, and DSPs from Apple, Arm, Intel, MediaTek,

TabNine is an AI-powered code completion engine that runs a deep-learning model to generate real-time code suggestions across all programming languages. It operates as an editor plugin that communicates with a backend through a JSON message-passing interface, processing code entirely on the local machine or within a private cloud to keep source code secure and private. The system provides a completion request API that accepts cursor context and returns ranked text completions, with features for configuring completion regions, prefetching files for indexing, and managing binary versions and up

Ente is a privacy-focused platform for end-to-end encrypted storage and two-factor authentication management. It functions as a zero-knowledge identity provider, ensuring that all cryptographic operations, key derivation, and data encryption occur locally on the user's device. By maintaining this architecture, the service provider remains unable to access or decrypt any stored personal information or authentication credentials. The platform distinguishes itself through a combination of on-device intelligence and resilient data distribution. It utilizes a local machine learning engine to perfo

The Hugging Face Hub Python client is a library that provides programmatic access to the Hugging Face Hub, a centralized platform for hosting and collaborating on machine learning models, datasets, and demo applications. It serves as the primary SDK for interacting with the Hub's API, enabling users to download and upload models and datasets, manage repositories, authenticate via tokens or OAuth, and run inference on hosted models through a unified interface. The client distinguishes itself through a comprehensive set of capabilities that go beyond basic file transfer. It includes a CLI exten

MediaPipe is a cross-platform machine learning framework designed for building and deploying pipelines that process live and streaming media. It provides a system for connecting processing components into custom machine learning chains to analyze real-time audio and video streams. The framework includes a suite of pre-trained models for tasks such as hand, face, and pose tracking, along with tools for retraining and customizing these models with specific datasets. It also features a dedicated benchmarker for measuring the execution speed and accuracy of machine learning models directly within

MiniCPM is a collection of small language models designed for local, on-device deployment in resource-constrained environments. The project focuses on running dense Transformer models on consumer hardware, including GPUs, CPUs, and Apple Silicon, without requiring custom code forks. The project distinguishes itself through heavy optimization for edge hardware, utilizing quantized weight compression in GGUF and MLX formats to reduce memory overhead. It implements advanced inference techniques such as speculative sampling and radix-tree prefix caching to accelerate generation speed and throughp

Sglang is a high-performance inference engine and serving system designed for large language and multimodal models. It provides a programmable interface for orchestrating complex generation workflows, enabling developers to coordinate multi-turn dialogues, tool invocations, and reasoning chains through a domain-specific language. The platform is built to support production-scale deployments, offering an OpenAI-compatible API that allows for integration with existing application ecosystems. The system distinguishes itself through a disaggregated architecture that separates compute-intensive pr

mistral.rs is an inference engine for large language models that runs locally and exposes models behind OpenAI and Anthropic-compatible APIs. It serves as a multi-model serving platform, capable of loading several models in a single server process with per-request routing and on-demand loading and unloading. The engine supports multimodal inference, processing text alongside images, video, audio, and speech inputs, and includes a quantized model deployment runtime that reduces memory use and speeds up inference on consumer hardware. The project distinguishes itself through an agentic tool exe

Serge is a self-hosted web chat interface for running large language models locally using the llama.cpp inference engine. It loads GGUF-format model files directly on your own machine, removing the need for internet connectivity or external API keys, and streams responses to the browser in real time via WebSocket connections. The project is packaged for containerized deployment using Docker and Docker Compose, with a Traefik reverse proxy that handles HTTP and WebSocket routing along with automatic TLS certificate management. Ready-made Kubernetes manifests are also provided, enabling deploym

LiteRT is a runtime and API for executing machine learning and generative AI models on mobile, desktop, and IoT hardware. It consists of an inference engine and a specialized environment for running quantized large language and diffusion models locally on edge hardware. The system includes an ahead-of-time model compiler that translates models into hardware-specific bytecode to reduce startup latency and memory overhead. It provides a unified interface for Neural Processing Units with automatic fallback routing to CPUs or GPUs when specific subgraph support is unavailable. An edge model conve

The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.

QwenPaw is a framework for deploying personalized AI assistants and a multi-agent orchestration system. It enables the management of independent AI agents with specialized roles to solve complex tasks through coordinated communication. The system also serves as a local deployment tool for large language models and a gateway for integrating AI assistants with various messaging platforms. The framework is distinguished by an extensible plugin system that allows for the auto-loading of custom skills and functional modules. It features a reflective memory system that evolves the assistant's long-

This project is a vision language model framework and vision-to-text pipeline designed for deploying and optimizing models that process both images and text. It provides an on-device inference engine and a vision language model framework to run quantized models locally on mobile and desktop hardware accelerators. The framework features a model quantization toolkit to reduce weight precision for lower memory footprints and increased execution speed on specialized silicon. It also includes an efficient vision encoder utilizing a hybrid encoding system to compress image tokens, which reduces pro

Cactus is an on-device AI inference engine designed for executing large language models, vision models, and speech-to-text systems on mobile and wearable hardware. It provides a programmable tensor computation graph for defining sequences of matrix operations and activation functions, alongside a local retrieval augmented generation framework that grounds model responses using local text files. The project features a multiplatform SDK with language bindings for integrating AI capabilities into mobile applications and a model conversion system that transforms external model formats for optimiz

MiniCPM-V is a multimodal large language model and vision-language system designed for complex visual and linguistic understanding. It functions as an on-device AI model, providing the capacity to process text, images, and video as a compact neural network. The project is specifically developed as an edge AI framework, utilizing quantization and weight sharding to run on memory-constrained mobile chipsets. This allows for the deployment of multimodal intelligence directly on mobile operating systems for local inference. Its capabilities cover multimodal content analysis of high-resolution im

Doctor-Dignity is a privacy-preserving medical AI framework designed to execute large language models and diagnostic reasoning tasks locally on edge hardware. It provides a local inference engine and retrieval augmented generation implementation that ensures sensitive health data remains offline by removing dependencies on external cloud servers and internet connectivity. The project includes a medical fine-tuning framework for adapting base language models to specialized clinical domains using parameter-efficient methods. To enable execution on resource-constrained and mobile devices, it pro

Khoj is a self-hosted artificial intelligence platform designed for personal knowledge management and semantic information retrieval. It functions as a private assistant that indexes your local documents, notes, and external workspaces, allowing you to interact with your data through natural language queries and conversational chat. By maintaining a local-first architecture, the system ensures that your information remains under your control while providing context-aware responses grounded in your personal knowledge base. The platform distinguishes itself through a modular, cross-platform int

ncnn is a high-performance neural network inference framework designed for executing deep learning models locally on mobile and desktop hardware. It functions as a specialized engine that enables the deployment of artificial intelligence tasks directly on resource-constrained devices, eliminating the need for external network connectivity or cloud-based processing services. The framework provides a comprehensive toolset for model optimization, allowing users to convert and quantize machine learning models into specialized binary structures. By utilizing static model graph compilation and zero

WeClone is an end-to-end framework designed for the creation, training, and deployment of personalized conversational AI digital twins. By fine-tuning large language models on individual chat history, the platform enables the replication of unique communication styles, speech patterns, and conversational habits. The system manages the entire lifecycle of these digital avatars, from initial data preparation to final integration into messaging platforms for real-time interaction. The platform distinguishes itself through a comprehensive suite of data processing utilities that prepare raw messag

This project is a development framework for building edge-based AI agents that perform multimodal inference and system-level automation directly on mobile devices. By prioritizing local-first execution, the platform ensures data privacy and offline functionality, allowing developers to run large language models on hardware without requiring external server connectivity. The framework distinguishes itself through an integrated orchestration layer that connects language models to custom tools, scripts, and native device intents. It provides a structured registry for mapping natural language ins

Second-Me is a framework for orchestrating local agent tasks and fine-tuning personal language models. It provides a system for training specialized assistants on local datasets to support custom knowledge retrieval and task execution requirements. The project distinguishes itself through a modular architecture that manages the lifecycle of machine learning tasks. It includes a state manager that persists intermediate training progress to local storage, allowing for the interruption and resumption of long-running configuration processes. Furthermore, the system utilizes standardized protocols

MiniCPM-o is a multimodal large language model designed to function as a real-time conversational assistant on edge devices. By mapping text, image, video, and audio inputs into a unified latent space, the system enables simultaneous cross-modal reasoning and full-duplex interaction. It is built as an edge-side inference engine, utilizing quantized model weights to maintain high-performance processing on consumer hardware. The system distinguishes itself through its integrated speech synthesis and voice cloning capabilities, which allow for the generation of expressive, personalized vocal out

MediaPipe is a cross-platform machine learning framework designed for deploying vision, audio, and text processing models across mobile, desktop, and web environments. It functions as an on-device inference engine that executes complex models locally on edge hardware, ensuring low latency and privacy without requiring a constant internet connection. The framework utilizes a graph-based pipeline orchestration system where data flows through a directed network of modular calculators to ensure synchronized and deterministic processing. It distinguishes itself through a unified runtime that provi

Danswer is an LLM application framework and RAG engine that provides a self-hosted interface for connecting large language models to private data. It serves as an enterprise AI chat interface and agent orchestrator, enabling the creation of specialized assistants with custom instructions and knowledge bases. The platform differentiates itself through an observability dashboard for tracking query history and token consumption, as well as a white-labeled interface for customized branding. It includes a multi-step research workflow for producing long-form reports and a sandboxed environment for

This project is a self-hosted large language model chat interface and AI model aggregator. It provides a unified web environment for interacting with multiple AI providers and local models, acting as a provider-agnostic API gateway to standardize requests across different endpoints. The platform functions as an agentic AI framework and generative UI workspace, enabling the construction of specialized assistants with custom instructions and subagents. It features a sandboxed code interpreter for secure execution of multiple programming languages and a generative UI system that renders interact

This project is a framework for running Stable Diffusion image generation models on Apple Silicon using Core ML hardware acceleration. It provides a local generative AI pipeline for producing images from text prompts using Swift and Python without relying on external cloud APIs. The system includes a model converter to transform deep learning checkpoints into Core ML formats and a model optimizer to quantize weights and activations. It features a ControlNet integration layer to guide image generation using external signals such as edge and depth maps. Capabilities cover text-to-image generat