MeshioMeshio

open-source

8 articles tagged “open-source”, most recent first.

C
Sep 8, 20261 min read

Hugging Face and Earthmover simplify open AI weather forecasting

A new workflow targets the data, storage, and GPU hurdles that make open weather models harder to use than they look.

A
Sep 8, 20261 min read

TranslatePsy-AfriSLM brings on-device translation to 19 African languages

A new open-source translation suite targets offline, affordable AI access with models as small as 0.8B parameters.

D
Sep 7, 20261 min read

Open Yap 1K brings 1,000 hours of natural speech to voice AI builders

A new commercial-use dataset captures the interruptions, overlap and room noise that full-duplex voice models usually miss.

A
Sep 4, 20261 min read

Open Armenian LLM project releases data, model and full training recipe

A new open ecosystem gives Armenian AI developers inspectable data, reproducible training materials and a model that tops existing open benchmarks.

VLANeXt Offers an Open Recipe Book for Building Stronger Robot AI
Aug 31, 20261 min read

VLANeXt Offers an Open Recipe Book for Building Stronger Robot AI

A new research codebase distills more than 500 VLA experiments into practical baselines for robotics foundation-model development.

three.ws Packages 3D Bodies, Agent Logic and Payments in One Open-Source Stack
Aug 29, 20261 min read

three.ws Packages 3D Bodies, Agent Logic and Payments in One Open-Source Stack

The three.ws project combines generative 3D avatars, agent memory, tool use and autonomous USDC payments across several developer surfaces.

SenseTime previews NEO-unify, an encoder-free multimodal model
Aug 28, 20261 min read

SenseTime previews NEO-unify, an encoder-free multimodal model

NEO-unify combines native text and pixel processing in one end-to-end architecture, promising more efficient multimodal training.

Hugging Face guide maps the best local LLMs for 2026 hardware
Aug 27, 20261 min read

Hugging Face guide maps the best local LLMs for 2026 hardware

A new Hugging Face guide compares local models by hardware, licensing, context length, and real-world AI development needs.