Back
Information Technology
Coding Gateway in Greenative Studio

Avgidea Adds Local LLM Coding to Greenative Studio for Mac

Avgidea Inc.

Key Facts:

  • Avgidea, Inc. has released a major update to Greenative Studio, its private AI workbench for Mac, adding an Anthropic-compatible API gateway that allows agentic coding tools such as Claude Code to run against large language models executing entirely on the user's local machine.
  • The update addresses growing concerns among development teams — particularly in Australia and New Zealand — about proprietary source code being sent to cloud AI services, enabling the same agentic workflows to run locally with no code or prompts leaving the device.
  • New model support includes NVIDIA's Nemotron 3.5 Lightning, a 30-billion-parameter mixture-of-experts model optimised for agentic tasks, alongside additions to the model catalogue including Google's Gemma 4 26B and Qwen-family models.
  • Additional features include a real-time token metrics dashboard, one-click model start-up requiring no command-line configuration, and a focus on open-weight models released under permissive licences such as Apache 2.0 and MIT.
  • The Coding release is available as part of the Greenative Studio Pro plan at US$18 per month or US$180 per year, with no per-token charges for local workflows; a free plan with Phi-4-mini is also available with no credit card required.

Coding agents such as Claude Code can now run against local models on Apple Silicon

Tokyo, Japan — September 3, 2026 — Avgidea, Inc., a Japan-based developer of data and AI platforms, today announced a major update to Greenative Studio, its private AI workbench for Mac. The new Coding release adds an Anthropic-compatible API gateway that lets agentic coding tools — including Claude Code — run against large language models executing locally on the user's Mac, and introduces support for NVIDIA's newly released Nemotron 3.5 Lightning model.

 

For many businesses, source code is among their most sensitive intellectual property. As agentic coding tools become part of everyday development work, more teams in Australia and New Zealand are weighing the productivity gains against a simple concern: every prompt may carry proprietary code to a cloud service. The Coding update gives those teams another option — running the same agentic workflows against a model that never leaves their machine.

 

With the update, developers can point Anthropic-compatible coding tools at a local endpoint served by Greenative Studio. In internal testing, Claude Code connected to a locally running model was able to explore a multi-thousand-line codebase — reading files, running shell commands, recovering from errors, and producing an accurate architectural summary — with no code or prompts sent to any cloud AI service.

 

 

"Source code deserves the same protection as any confidential business document," said Teppei Yagihashi, founder of Avgidea. "Agentic coding is transforming how software gets built, but it shouldn't require sending your repository to someone else's servers. With this update, the agent's brain runs on your own Mac — your code, your prompts, and your model all stay local."

 

 

Key additions in the Coding release include:

 

  • An Anthropic-compatible API gateway for agentic coding tools, compatible with Claude Code and other Anthropic-compatible clients

  • Support for NVIDIA's Nemotron 3.5 Lightning, a 30-billion-parameter mixture-of-experts model designed for agentic workloads such as tool calling, code review, and task execution

  • An expanded model catalogue, adding Google's Gemma 4 26B (A4B) and Qwen-family models

  • A real-time token metrics dashboard showing generation speed and cumulative token usage for local coding sessions

  • One-click model start-up — no Python, Homebrew, or command-line configuration required

 

Greenative Studio continues to focus on curated open-weight models released under permissive licences (e.g. Apache 2.0, MIT, OpenMDW), helping businesses evaluate local AI workflows with clearer commercial-use expectations.

 

The largest models in the catalogue require an Apple Silicon Mac with at least 32 GB of unified memory. In Avgidea's testing on an M4 Max Mac with 128 GB of unified memory (Q8 build), Nemotron 3.5 Lightning sustained approximately 70–80 generated tokens per second during agentic coding sessions. Lighter models, including the free Phi-4-mini plan, remain available for Macs with less memory.

 

The Coding release is included in the Greenative Studio Pro plan at US$18 per month (approx. AU$28) or US$180 per year, with fixed pricing and no per-token usage charges for local workflows. A free plan with Phi-4-mini is available, and new users can start without a credit card.

 

Media assets

High-resolution product screenshots and logo files are available at: https://www.avgidea.io/en/press. Images may be used for editorial coverage of Greenative Studio.

 

Claude Code is a product of Anthropic, PBC. Greenative Studio is an independent product and is not affiliated with, sponsored by, or endorsed by Anthropic or any of the model providers named in this release. All other product and model names are trademarks of their respective holders.

 


About us:

About Avgidea

Avgidea, Inc. is a Japan-based software company developing data and AI platforms for business use. Its products include Greenative Studio, a desktop app for local AI workflows on Mac, and Greenative Platform, a data platform connecting AI workflows with business data, cloud storage, databases, and internal systems, which is used in production by businesses today. For more information, visit https://www.avgidea.io/en.

 


Contact details:

Teppei Yagihashi Founder, Avgidea, Inc. Email: [email protected]

Avgidea, Inc.