Patterns worth adopting
Open-source learning notes
RStack can learn from open-source agent frameworks without copying code blindly:- OpenAI Agents SDK emphasizes multi-agent workflows, tracing, handoffs, and model-provider flexibility.
- Model Context Protocol emphasizes standardized context/tool interfaces and schema-first interoperability.
- Google ADK emphasizes code-first agents, evaluation, deployment, and control.
- AI SDLC reference architectures emphasize governance, tool orchestration, observability, human gates, and enterprise policy.
Use those projects as design references. Do not paste their code or prompts into RStack unless the license is compatible and attribution is preserved.
Current loopholes in the application
Recommended next sprint
- Pack installer —
rstack-agents packs install backend-development unit-testing security-scanning. - Usage ingestion — allow host frameworks to write
.rstack/runs/<run-id>/usage.jsonl. - Validator sandbox runner — enforce read-only validator tools at the RStack bridge layer.
- Dashboard diagnostics — show missing contract/event reasons per Business Flex panel.
- Safe OSS import — license-aware agent/plugin adaptation workflow.
- MCP adapter — expose core SDLC tools through a standard context/tool protocol.
Decision rule for business users
If the user says “upgrade this application”, do not enable the entire catalog. Start with:business-flexfor production/business worklean-mvpfor prototypesenterprise-webappfor compliance-heavy web apps
.rstack/rstack.config.json to the smallest domains required by the request.