JFrog announces ‘agentic repo’ for AI-driven development

JFrog has introduced JFrog Fly, an offering the company describes as a zero-config, “agentic repository” for accelerating AI-driven software development.

Introduced September 9, JFrog Fly is intended to support agentic workflows for development teams. AI agents orchestrate artifacts across the software life cycle, enabling developers to focus on delivering software to production with speed and scale, according to JFrog. Developers can join a beta waitlist for JFrog Fly.

Built atop the JFrog Software Supply Chain Platform, JFrog Fly is designed to offer small development teams an AI-driven experience tightly integrated with GitHub and native AI tools like Cursor, Claude Code, and GitHub Copilot, JFrog said. JFrog Fly can integrate with other AI repos and platforms Model Context Protocol standards, ensuring all agents operate consistently with context-aware decision-making across different systems, the company said.

JFrog said its new offering aims to enable reliable, fast software delivery by:

Providing centralized management of all agentic artifacts and containers, aiding in easy sharing, storage, and distribution of release versions, accelerating software delivery at the pace of vibe coding.

Enabling clear, semantic release metadata, offering insight and context around release changes, so developers can make informed decisions about upgrading or integrating new versions.

Seamlessly integrating with agentic development environments, package managers, and GitHub repositories, enabling automatic tech stack detection and setup in a few clicks.