Hi everyone! I wanted to share an open-source project I’ve been building: Jules Ecosystem, a production-oriented autonomous software engineering platform designed to put Google Jules at the center of a controlled, multi-product development system.
Instead of just a single tool, the ecosystem provides three independent products powered by shared protocols and rigorous safety guardrails:
- Jules Extension: Bring Jules directly into your existing VS Code environment.
- Jules Coding IDE: A standalone AI-native coding environment built around Jules.
- Jules Code CLI: A terminal-first autonomous coding agent in the category of tools like Claude Code.
Architecture & Principles
The core architecture principle is that Jules is the primary intelligence, while the independent products act as clients governed by deterministic infrastructure. When design choices conflict, decisions strictly follow this priority hierarchy:
CORRECTNESS > SAFETY > VERIFIABILITY > RELIABILITY > RECOVERABILITY > PERFORMANCE > COST > SPEED
Key Features & Safety
- Bounded Agent Loop: Interpret → Inspect → Plan → Policy Check → Execute → Observe → Verify → Repair.
- Independent Claim Verification: Code claims are independently executed (
npm run build,npm test) prior to any merge. - Zero Trust Security Boundary: Built with a Sandboxed Execution Broker, default-DENY network policies, and automatic secret redaction.
Check out the full repository and documentation (including threat models, usage guides, and architecture audits) on GitHub:
[Link to your GitHub Repository: https://github.com/Harshil-0011/Jules-For-VS-Code\]
I’d love to hear your thoughts, feedback, or ideas from fellow developers working with AI agents!