CCStudio™ Edge AI Toolkit Extension Release Notes
v1.0.0

Release Notes — CCStudio™ Edge AI Toolkit Extension v1.0.0

Initial release — November 2026

General Information

CCStudio™ Edge AI Toolkit Extension v1.0.0 is the initial release. It is a VS Code extension for CCStudio™ IDE and VS Code®. It detects, installs, and updates the environment needed for TI Edge AI (TinyML) workflows: a local Python interpreter, the TinyML ModelZoo training and compilation toolchain, and the TinyML AI Skills that teach your AI coding agent the workflow. For a full summary, see the What’s New section below.

Once installed and configured, it will provide Edge AI Agentic workflow capabilities inside CCStudio™ IDE or CCStudio™ for VS Code, including dataset management, model training and optimization, and importing trained models into your CCStudio projects, for compiling, loading, running live inference, and debugging on device. The included agent skills system provides your AI agent with knowledge of all the features and settings needed for Edge AI development on TI devices, so it can answer specific questions, offer model or device recommendations, or guide you through an entire development workflow. Try it out, and start prompting it with the Edge AI application you want to build!

System Requirements

Note

The extension requires CCStudio IDE v21.x or VS Code 1.82 or later, and an internet connection to download packages from https://dev.ti.com/tirex.

Windows
  • Windows 10 / 11 64-bit
Linux
  • 64-bit Linux
macOS
  • macOS 27 / 26 / 15

Python

The TI Neural Network Compiler (NNC) v2.1.2 only supports Python 3.10.x. The extension installs its own local copy of Python 3.10 so your system Python is never modified. Alternatively, you can select your own Python 3.10.x interpreter or virtual environment with Select Python… (setting edgeai.pythonPath). The system PATH is not searched.

Installation

1. Install a Supported IDE
  • CCStudio™ IDE: any v21.x version.
  • VS Code®: set up CCStudio for VS Code.
2. Install the CCStudio™ Edge AI Toolkit Extension

VS Code

  1. Open the Extensions view and search for CCStudio Edge AI Toolkit in the VS Code Marketplace.
  2. Click Install.

CCStudio IDE

  1. Download the latest ti-developer-tools.edgeai-toolkit.vsix from TI.com.
  2. In the CCStudio IDE, open the Extension view, and use the Install from VSIX… option and select the downloaded file.
3. Run the Setup Wizard
  1. The extension activates on startup and checks for the Edge AI Toolkit components and their dependencies. The Setup panel opens automatically on first run if anything needs attention.
  2. To open it manually, press Ctrl+Shift+P and run CCStudio Edge AI Toolkit: Open Setup, or click the status bar item (bottom right).
  3. Work through the steps in order using Install, Update, or Retry. Missing components are downloaded and installed in the background. Click Re-check to re-run detection.

The following components are installed:

  • Python 3.10 (required by the TI Neural Network Compiler)
  • TinyML ModelZoo v1.5 (can take several minutes, as it installs the Python packages and their dependencies)
  • TinyML AI Skills, installed to C:\ti on Windows or ~/ti elsewhere, where the AI Assistant Configurator picks them up automatically
Note — Install Locations

Downloaded Python and ModelZoo packages are installed to %LOCALAPPDATA%\Texas Instruments\edgeai on Windows, ~/Library/Application Support/Texas Instruments/edgeai on macOS, and ~/.local/share/Texas Instruments/edgeai on Linux (configurable with edgeai.installDir).

4. Set Up Your AI Agent

Use the AI Assistant Configurator view in the IDE to set up your AI agent, LLM key, and related settings. Then see Get Started to begin developing with your agent.

CCStudio™ Edge AI Toolkit Extension v1.0.0 — What’s New

Features
  • Guided setup of the Edge AI environment from a single Setup panel
    • Local Python 3.10 interpreter, or your own 3.10.x interpreter / virtual environment
    • TinyML ModelZoo for dataset management, model training and optimization, and compilation
    • TinyML AI Skills that teach your AI agent the end-to-end Edge AI workflow
    • CCStudio for VS Code extension
  • Status bar indicator showing whether your environment is ready or needs attention
  • Update notifications when newer ModelZoo, Skills, or Python packages are available
  • Automatic AI agent configuration, so your agent can find the installed Python and ModelZoo with no manual setup
  • Starter prompts to help you begin working with your AI agent

Components

Components & Versions
Step Component Required Version Description
0 CCStudio for VS Code extension Latest Adds Code Composer Studio project, build, and debug support to VS Code. Installed from the VS Code Marketplace.
1 Python 3.10.x Runtime for TinyML ModelZoo. Local copy installed by the extension, or a user-selected interpreter.
2 TinyML ModelZoo 1.5.0+ TI’s toolchain for training, quantizing, and compiling TinyML models for TI devices.
3 TinyML AI Skills 1.5.0+ Skills that teach your AI agent to configure, train, compile, and deploy TinyML models.

Supported Devices

The following device families are supported by TinyML ModelZoo v1.5.0.

Device Families at a Glance
Family Devices CPU Core Hardware NPU
C2000 F28x F28P55, F28P65, F28P551x, F2837, F2837xS, F2838x, F2807x, F28003, F28004, F28002x, F280013, F280015, F28E12 TI C28x DSP F28P55
C2000 F29x F29H85, F29P58, F29P32 TI C29x DSP None
MSPM0 MSPM0G3507, MSPM0G3519, MSPM0G5187 Arm Cortex-M0+ MSPM0G5187
MSPM33C MSPM33C32, MSPM33C34 Arm Cortex-M33 MSPM33C34 (no model support in this release)
AM13 AM13E2 Arm Cortex-M33 AM13E2
AM26x AM263, AM263P, AM261 Arm Cortex-R5F None
Connectivity CC2755, CC2745, CC1312, CC1314, CC1352, CC1354, CC35X1 Arm Cortex-M33 / Cortex-M4 None (CC2755, CC2745, CC35X1 use the Arm Custom Datapath Extension)
Radar IWRL6432 Arm Cortex-M4 None

Configuration

Commands
Command Description
CCStudio Edge AI Toolkit: Open Setup Opens the Setup panel.
CCStudio Edge AI Toolkit: Re-enable Setup Reminders Undoes “Don’t remind me”.
Settings
Setting Scope Description
edgeai.pythonPath Machine-overridable Path to the Python executable. If empty, the Edge AI Python package installed by the extension is used.
edgeai.installDir Machine Where downloaded Python and ModelZoo packages are installed.
Note — Workspace Trust

machine settings can only be set in user (or remote) settings; a repository’s .vscode/settings.json cannot change them. In an untrusted workspace, only your user-level edgeai.pythonPath is used.

Proxy

Downloads (package server and pip) use the proxy from your user VS Code http.proxy setting if set, otherwise the HTTPS_PROXY / HTTP_PROXY environment variables. A workspace’s http.proxy is ignored. All packages are downloaded from https://dev.ti.com/tirex.

Get Started

Once all components are ready, go through the CCStudio AI Configurator to set up your AI agent, then try asking:

  • Explore: “What Edge AI tasks and models are available for my device?”
  • Train: “Help me train a model for my device.”
  • Deploy: “Deploy my trained model to my device.”
Watch the Video — an introduction to the features of CCStudio™ Edge AI Toolkit.
TinyML ModelZoo Documentation — full reference documentation.
Tip

For best results, uninstall any TinyML agent skills that were manually installed globally. Skills installed by this extension do not need to be removed.

Manifest

The software manifest lists the components and licenses delivered with this release.

Software Manifest — CCStudio™ Edge AI Toolkit Extension v1.0.0.