V0.9.0
projectdiscovery/katanaV0.9.0Jun 9, 2025by danielcampagnolitg
AI Summary
A massive release involving AI-generated code (79k lines added), focusing on autonomous agents, database implementations (Postgres/Mongo), and a TypeScript redesign for frontend/backend integration.
Key Highlights
- AI-generated code using Gemini 2.5 Pro/Flash
- Image support added to the autonomous agent
- Initial Postgres and Mongo implementations
- Strong static typed design with shared interfaces
- Autonomous agent iteration details saved with UI visibility
Breaking Changes
- Replaced Aider with a TypeScript search/replace editor
New Features
- Image support for autonomous agents
- Database implementations (Postgres and Mongo)
- Strong static typed design
- Agent iteration UI for debugging
- 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