AREPL is a VS Code extension that evaluates Python code in real-time as you type, displaying variables, errors, and print output in a side panel. It provides a scratchpad-like experience for Python development, with features like real-time evaluation, variable inspection, error display, and support for dumping variables from functions. The extension uses a Python backend (arepl-backend npm package) to execute code and communicate results via JSON. The TypeScript architecture includes a PreviewManager that orchestrates execution and preview updates, a PreviewContainer that manages the webview, and separate modules for inline errors (PythonInlinePreview) and panel display (PythonPanelPreview). The codebase is well-structured with clear separation of concerns, includes unit tests (mocha), and uses telemetry for diagnostics. The extension is maintained (last release November 2024) and uses modern dependencies.
diart is a Python library and CLI tool for real-time online speaker diarization, built on top of pyannote.audio. It processes audio streams (microphone, files, WebSocket) with low latency using a modular pipeline of segmentation, embedding, clustering, and aggregation blocks. The library is designed for both streaming and offline evaluation, with support for overlap-aware processing and hyperparameter tuning via Optuna. It provides a reactive streaming architecture using RxPY, making it suitable for building AI-powered audio applications. The repository includes a benchmark suite, expected outputs for standard diarization datasets (AMI, DIHARD, VoxConverse), and CI/CD pipelines. While primarily a software library, it has a strong research component with published results and reproducibility artifacts.
FastRTC is a Python library that enables developers to build real-time audio/video streaming applications with minimal code. It provides a high-level `Stream` class that integrates with Gradio for automatic UI generation and supports both WebRTC and WebSocket protocols. The library includes built-in handlers for voice activity detection (VAD) via Silero, speech-to-text via Moonshine, text-to-speech via Kokoro/Cartesia, and turn-taking logic. It also offers TURN credential helpers for Cloudflare, Twilio, and Hugging Face. The architecture revolves around defining a handler function that processes media chunks, wrapping it with turn-taking decorators, and creating a Stream object that handles signaling, connection management, and UI rendering. The codebase is actively maintained with frequent commits and an extensive set of demos integrating with various LLMs and AI services.
BeatNet is a Python library for real-time and offline music beat, downbeat, tempo, and meter tracking. It provides a complete system comprising a CRNN-based neural network for feature extraction, particle filtering for causal inference, and DBN for non-causal inference. The library supports four operational modes: streaming (microphone input), real-time (file processing), online (fast file processing), and offline (DBN-based). Beyond inference, it includes a complete training pipeline for training the CRNN model on custom datasets with data preparation tools, dataset handling, and validation procedures. The architecture is modular with clear separation between feature extraction, neural network modeling, and inference algorithms.
This repository implements Composite, a component-based research operating system where kernel policies (scheduling, memory management, synchronization) are implemented as user-level components. It runs on x86-32, x86-64, and ARMv7a architectures, primarily under QEMU. The system provides a minimal kernel with capability-based security, synchronous invocation (sinv) for inter-component communication, and shared-memory channels. It includes a full musl libc port for POSIX compatibility, a DPDK-based network stack, an lwIP adapter for TCP/IP, and a simple VMM with virtio-net and device emulation. The architecture is closer to a microkernel than a traditional monolithic kernel, with components loaded and composed via a Rust-based composer tool that reads TOML specifications. A large suite of microbenchmarks measures IPC, scheduling, and synchronization latency. The codebase is pre-alpha quality, with many FIXMEs and incomplete features, but demonstrates strong craftsmanship in its abstraction layers (assembly stubs, channel library, scheduler framework, perfdata utility).
This repository implements Mobile-GS, a real-time Gaussian splatting approach for novel view synthesis optimized for mobile devices. The system trains 3D Gaussian representations from multi-view images, applies compression techniques (vector quantization, Huffman coding, GPCC) to reduce model size, and renders novel views via differentiable EWA (Elliptical Weighted Average) splatting. It includes training pipelines (train.py, pretrain.py), rendering engine (gaussian_renderer/), scene management, custom CUDA kernels for efficient rasterization, and evaluation metrics. The architecture follows a modular design with separate components for training, rendering, scene handling, and compression, optimized for deployment on mobile platforms with limited computational resources.
This repository is a mobile SDK for real-time interactive AI avatars, primarily targeting Android and iOS platforms. It provides on-device inference for speech recognition (via WeNet) and face/body segmentation (via ncnn-based U-Net models), enabling low-latency lip-sync and avatar animation driven by audio input. The SDK is structured as a C++ core with platform-specific wrappers (Java for Android, Objective-C for iOS), and includes bundled third-party libraries (ncnn, OpenCV, FFmpeg, ONNX Runtime) for computer vision, audio processing, and neural network inference. In production, the system ingests 16kHz PCM audio from a microphone, extracts MFCC features, runs streaming speech recognition, and simultaneously processes the audio through a U-Net model to generate facial animation frames. These frames are rendered using OpenGL ES (Android) or Metal (iOS) with alpha blending for compositing onto a background. The SDK also includes model download, encryption (AES-128-CBC), and resource management utilities. The architecture is monolithic: all core logic lives in a single C++ module (duix-sdk), with platform-specific integration code in the app directories. The demo app in Android provides a fully functional test harness. While the SDK is feature-complete and demonstrates significant engineering effort in mobile AI inference, the codebase exhibits several quality issues: duplicated third-party headers across architectures, hardcoded encryption keys, outdated library versions (OpenCV 4.6.0, ncnn 2022/2023), and minimal inline documentation. The high star count and fork activity suggest a strong community, but the code itself is functional rather than exemplar. The most reusable components are the reference-counted memory allocator (dh_mem.h) and the AES stream decryption wrapper (gaes_stream.h), which can be extracted for general-purpose use.
LiveCanvas is a collaborative whiteboard and diagramming web application built with Next.js 14, Convex as the real-time backend, and Kinde for authentication. It allows users to create teams, manage files, and edit documents using Editor.js alongside an Excalidraw-based canvas for freeform drawing. The architecture follows a standard Next.js App Router pattern with client-side rendering for authenticated routes and server components for the landing page. Data flows through Convex mutations and queries, with file content (document JSON and whiteboard elements) persisted as strings. The application is functional but exhibits several minor issues: the dark mode CSS is incorrectly defined (identical to light mode), there are typos in mutation argument names ('archieved' instead of 'archived'), and the codebase lacks tests or CI/CD configuration. While it demonstrates integration of multiple third-party libraries, the components are tightly coupled to the app's specific data model and are not easily reusable outside this project.
This repository is a small Python demo application that turns a webcam feed into a real-time David Attenborough-style nature documentary narration. It consists of two independent processes: capture.py grabs frames from the webcam every 2 seconds, resizes them to a maximum dimension of 250 pixels, and writes them to frames/frame.jpg; narrator.py polls that file, base64-encodes it, sends it to OpenAI's GPT-4 Vision API with a snarky Attenborough system prompt, appends the response to a running conversation script, synthesizes speech via ElevenLabs, and plays the audio aloud. The two processes communicate through the filesystem, which is a simple but effective decoupling pattern for a demo. The code is functional and readable, with a few thoughtful touches: the image is downscaled before upload to reduce API cost and latency, and the narrator retries reading the frame file when it catches a transient EACCES error caused by the capture process writing concurrently. However, it is a proof-of-concept rather than a production application: there are no tests, no error handling for API failures, hardcoded paths, and the pinned dependencies are from late 2023. The OpenAI model 'gpt-4-vision-preview' and the ElevenLabs 'generate/play' API are both deprecated, so the code would need updates to run against current APIs. Despite a recent commit timestamp in the metadata, the codebase is effectively a frozen 2023 demo. The maintainer has not updated dependencies or addressed the deprecated APIs, and 41 open issues remain. It is best treated as a reference implementation or a starting point for a webcam-to-AI-narration pipeline, not as a maintained library.