Engineering governance and context for AI coding agents — the knowledge a senior engineer would have, compiled into every agent.
What is Rosetta
| AI coding agents are powerful — but hard to use consistently across a real team. Rosetta is an open-source governance and context layer that compiles your team's engineering knowledge — architecture, conventions, guardrails — into every agent, every session. Works with the tools you already use. Everything stays in your perimeter. |
Every AI interaction follows four phases: Prepare (load guardrails and context), Research (search the knowledge base), Plan (produce a reviewable plan), Act (execute with full context), and Validate (manual validation by AI). Read more in the Usage Guide.
Why use it
- Context engineering, not prompt hacking. Agents receive your conventions, architecture, and business rules automatically — structured, versioned, and ready before the first line of code. See how it fits your workflow.
- Write once, run everywhere. Agent-agnostic design adapts to any IDE and any tech stack. No per-tool maintenance.
- Guardrails built in. Approval gates, risk assessment, and data protection ensure consistent AI behavior across teams. See how Rosetta protects you.
- Cross-project intelligence (opt-in). Publish business and technical context from every project into a shared knowledge base. Agents see the system, not just one repo — trace flows across services, catch breaking API changes before they ship, and assess blast radius of any change across the portfolio.
- One-command onboarding. New repo, new developer — productive immediately with best practices baked in.
- Instructions as code. Prompts version-controlled with release management — single source of truth for all teams.
How it works
Your IDE connects to the Rosetta MCP server. The server exposes guardrails and common best practices, and provides a menu of available instructions — workflows and coding conventions. The coding agent selects only what it needs for the current task; Rosetta delivers just those, keeping the agent’s context lean. By design, no source code or project data reaches Rosetta.
Rosetta is designed to not see your source code or IP. It only serves knowledge and instructions to the agent. The agent loads only what it needs per request (progressive disclosure) and follows your organization’s workflows.
Get Started
Use Plugins when your IDE supports them. Plugins install Rosetta instructions locally and do not need a live Rosetta server connection during normal agent work.
Claude Code:
claude plugin marketplace add griddynamics/rosetta
claude plugin install rosetta@rosetta
Cursor, GitHub Copilot, and Codex: follow the plugin or standalone package instructions in Plugins.
Use MCPs for IDEs without a Rosetta plugin path, including Windsurf, Antigravity, OpenCode, and JetBrains Junie.
After installation, ask:
Greenfield (new repository): “Initialize this repository using the respective Rosetta workflow, this is a new repository, target tech stack: …, target architecture: …, business context: …”
Brownfield (existing repository): “Initialize this repository using the respective Rosetta workflow[, this is a composite workspace][, additional information]”
STDIO transport is available for air-gapped environments. All IDEs and detailed setup. Read more in the Quick Start.
Tech Demo
Supported IDEs and Agents
- Cursor
- Claude Code
- VS Code / GitHub Copilot
- JetBrains (Copilot, Junie)
- Windsurf
- Codex
- Antigravity
- OpenCode
Works with any MCP-compatible tool.
Documentation
| I want to… | Read |
|---|---|
| Understand what Rosetta is and how to think about it | Overview |
| Set up Rosetta | Quick Start |
| Learn how to use Rosetta flows | Usage Guide |
| Deploy Rosetta for my organization | Deployment |
| Understand the system architecture | Architecture |
| Navigate the codebase | Developer Guide |
| Contribute a change | Contributing |
| Debug a problem | Troubleshooting |
Contributing
Contributions welcome. See Contributing for workflow and expectations.
Community
License
See LICENSE for details.