Skip to Content

Neo on VS Code

Quick TL;DR

Neo is a local-first AI engineering agent for code, data, and ML workflows.

The VS Code extension lets you run multi-step tasks, debug environments, and manage data locally without uploading your code.

Install the extension, open a project folder, and start interacting with Neo from the sidebar or terminal in under 5 minutes.

Install VS Code ExtensionQuickstart Guide

What is the Neo Extension?

Local-first execution

All code and data stay on your machine with no external uploads required.

Encrypted vault

API keys and credentials stored locally, encrypted at rest.

Autonomous workflows

Automatically installs dependencies, handles errors, and self corrects code.


Architecture

Your Project Files

Source code and structure

Neo Runtime

Local AI agent orchestrator

Local Terminal

Executes scripts locally

Cloud APIs

AWS S3, Weights and Biases, Hugging Face

Cloud APIs are optional and only used when explicitly configured.


Platform vs VS Code Extension

Platform VS Code Extension
SetupNo setup required, just upload filesInstall extension, open a project folder, start Neo
Data50MB file limit or cloud storageConnect to S3 data buckets, GitHub code repositories, and local datasets directly
SecurityUpload to cloud environmentAll operations local, credentials stay encrypted on device
Best ForQuick prototyping and experimentationIterative development on your codebase for AI, ML, and data science tasks

AI and ML Tools and Integrations

Neo’s VS Code extension provides one-click integration with various third-party AI, ML, and data tools, enabling developers to build production-grade pipelines.

AWS S3

Load datasets and model checkpoints locally; configure API keys in vault.

Weights & Biases

Track experiments, logs, and artifacts automatically from VS Code.

Hugging Face

Access model hub locally; pull and push models securely.

Kaggle

Download datasets and competition files directly into project workspace.

More integrations coming soon

Additional tools and platforms in development.


Multi-Workspace Support

Isolated contexts

Each VS Code workspace runs a separate Neo instance, preventing interference.

No context leakage

Credentials, secrets, and project state stay workspace specific.

Parallel execution

Run multiple workspaces and tasks simultaneously without collisions.


Use Cases

Data pipelines

Automate fetching from S3, validating CSVs, and loading into databases.

Experiment tracking

Train ML models and log metrics to Weights and Biases automatically.

Environment fixes

Detect and fix dependency, Python version, and CUDA configuration issues in projects.

Model deployment

Package models and push to cloud registries or local containers.


Security

Local-only execution

Code, data, and credentials never leave your machine.

Training opt-out

Codebase is never used for AI model training or analytics.

Full control

Interrupt, review, and audit all automated actions.


Next Steps