GPT-SoVITS
GPT-SoVITS is a few-shot voice cloning and TTS WebUI that fine-tunes a speaker's voice from one minute of audio and supports zero-shot synthesis from a five-second sample.
HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
GPT-SoVITS is a few-shot voice cloning and TTS WebUI that fine-tunes a speaker's voice from one minute of audio and supports zero-shot synthesis from a five-second sample.
Pathway is a Python ETL framework for stream processing, real-time analytics, LLM pipelines and RAG, driven by a scalable Rust engine using Differential Dataflow.
Ultralytics YOLO26, YOLO11, YOLOv8 : object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
OpenMontage coordinates agent tools and pipelines for scripting, assembling, and rendering video projects.
Self-hosted AI gateway with a Rust core and Python SDK that calls 100+ LLM providers in OpenAI format, adding cost tracking, guardrails, and load balancing.
The best-benchmarked open-source AI memory system. And it's free.
CrewAI coordinates role-based AI agents into crews and event-driven flows, with tools for tasks, memory, tracing, and deployment.
PyTorch-based YOLOv5 from Ultralytics for object detection, instance segmentation, and classification, with training and export to ONNX, TensorRT, TFLite, and CoreML.
Deepfakes Software For All. Please see this forum post: Manifesto FaceSwap has ethical uses.
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
PPT Master turns documents or topics into natively editable PowerPoint decks with transitions, data-backed charts and audio narration from speaker notes.
The world's simplest facial recognition api for Python and the command line.
Odoo bundles CRM, eCommerce, accounting, warehouse and HR tools as web-based open source apps that combine into a full-featured ERP.
Agent skill that removes signs of AI-generated writing from text. It is plain Markdown, so it can run in any harness that supports skill-style instructions.
A framework for building document agents and retrieval applications.
A skill for your coding agent to stop it from burying the answer. ADHD-friendly output.
Supervision provides reusable building blocks for computer-vision pipelines, from detections and tracking to annotation and evaluation.
CLI-Anything generates command-line interfaces for desktop applications so agents can operate tools such as Blender, GIMP, Inkscape, Audacity, and LibreOffice through structured commands.
Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more.
Lightweight, open-source AI agent for your tools, chats, and workflows.