Starstruk Logo MarkStarstruk

V0.9.0

n4ze3m/page-assistV0.9.0Jun 9, 2025by danielcampagnolitg

AI Summary

A massive update utilizing AI (Gemini 2.5 Pro/Flash) to build the platform itself, resulting in a significant codebase expansion. Key focus areas include database implementations, static typing, and enhanced agent capabilities.

Key Highlights

  • Integration of Gemini 2.5 Pro/Flash for self-building and design updates
  • Introduction of Postgres and Mongo database implementations
  • Implementation of strong static typing with shared interfaces between frontend and backend
  • Addition of image support to the autonomous agent
  • Implementation of autonomous agent iteration details with a UI for debugging

New Features

  • Image support for autonomous agents
  • Postgres and Mongo database implementations
  • Strong static typed design with shared interfaces
  • Autonomous agent iteration details UI
  • Vector search for enhanced codebase intelligence
  • Code Tasks 'vibe coding' workflow

Full Release Notes

Huge release with 79k lines added, 32k lines removed, mostly from Gemini 2.5 Pro/Flash using the platform to build itself, updating the application design and docs for the AI as building this also becomes a blueprint for using AI to build applications.
Some highlights:
- Added image support to the autonomous agent
- Initial Postgres and Mongo (for Firestore Enterprise Edition) implementations with test suites shared between all db implementations
- New strong static typed design with shared interfaces and API definitions between the frontend and backed providing strong compile time checking, which is very useful when the AI is making changes across the front and backend.
- Replaced Aider with a TypeScript search/replace editor which will enable deeper integrations (review etc) into the coding agent.
- Autonomous agent iteration details are saved, with a UI to inspect, for greater visibility/debugging of the agents
- The beginnings of a Code Tasks a 'vibe coding'/AI assisted coding workflow (work in progress) and vector search for enhanced codebase intelligence for the agents.

Docs update coming soon