Skip to content

Prody

Prody is an autonomous AI cloud engineer that takes you from working code to a live, production-ready app on Google Cloud, without opening the GCP console or hiring a DevOps team.

Code Video Cerebral Valley

Core trick

Gates Cloud Run deployment on a passing security scan verdict and a human approval of the architect agent's diagram, then provisions via Google Cloud MCP.

Tags

dev toolsagentssecurity

Description

Prody is an autonomous AI cloud engineer that takes you from working code to a live, production-ready app on Google Cloud, without opening the GCP console or hiring a DevOps team. AI coding tools made it easy to build software, but shipping it safely still means dealing with security scans, infrastructure design, IAM, deployment configs, and post-launch monitoring. Solo developers, startup founders, and vibe coders often get stuck at exactly that gap. Prody closes it with a multi-agent pipeline orchestrated through Gemini Managed Agents (Interactions API): Architect designs GCP infrastructure and generates an architecture diagram Human approval means nothing deploys until you sign off Deploy provisions Cloud Run through Google Cloud MCP How it works: Each phase is a specialized agent (intake, security, architect, devops, SRE) with its own reasoning and tools, coordinated by an orchestrator that streams every step live over SSE. Security is a hard gate: the deploy agent refuses to run while the scan verdict is FAIL. When the gate passes and you approve the architecture, the DevOps agent calls Google Cloud MCP to provision real infrastructure and returns a live URL. The same session flows seamlessly between your IDE extension and the web dashboard, so you can start a scan in Cursor and approve the deploy from the browser. Why it is different and novel: Most AI DevOps tools stop at suggestions or dump a dashboard on you. Prody actually executes: it scans, fixes, plans, deploys, and monitors as a coordinated engineering team, not a single chatbot. Three things make it unique: Problem it solves: The missing engineering layer between AI-generated code and production. Secure, explainable, autonomous cloud operations for people who want to ship products, not become infrastructure experts.
pavan-gangadhar-001/deepmindhackathon2026★ 01 forksPythonCreated Jul 11, 2026 · last push Jul 11, 2026

README excerpt

# Multi-Agent GCP Deployment System

A command-line deployment assistant powered by Google's Gemini Interactions API and the Antigravity Managed Agent. It designs a Google Cloud architecture, generates an architecture diagram, waits for approval, and then deploys the application.

## How it works

The workflow has two agent phases with an automatic security gate between them:

1. **Cloud Architect**
   - Inspects the application directory.
   - Proposes a GCP architecture.
   - Generates `architecture.jpg` using Imagen.
   - Waits for the user to approve the design.

2. **Security gate (automatic)**
   - After approval and before any deployment, runs the local functional-testing + penetration-testing gate against the app directory.
   - Refuses to hand off to DevOps on a `FAIL` verdict (a broken or insecure app never ships). See [Pre-deploy security gate](#pre-deploy-security-gate).

3. **Senior DevOps**
   - Receives the approved architecture and conversation context.
   - Uses Google Cloud remote MCP servers where supported.
   - Uses non-interactive `gcloud` tools only for unsupported operations.
   - Reports deployment results and resource URLs.

## Google Cloud MCP servers

The DevOps agent uses these authenticated remote MCP servers:

- Cloud Run: `https://run.googleapis.com/mcp`
- Cloud Storage: `https://storage.googleapis.com/storage/mcp`
- Resource Manager: `https://cloudresourcemanager.googleapis.com/mcp`

Operations without a suitable Google Cloud MCP tool—such as

Team