OpenSage: Self-programming Agent Generation Engine

Agent development kits (ADKs) provide effective platforms and tooling for constructing agents, and their designs are critical to the constructed agents' performance, especially the functionality for agent topology, tools, and memory. However, current ADKs either lack sufficient functional support or rely on humans to manually design these components, limiting agents' generalizability and overall performance. We propose OpenSage, the first ADK that enables LLMs to automatically create agents with self-generated topology and toolsets while providing comprehensive and structured memory support. OpenSage offers effective functionality for agents to create and manage their own sub-agents and toolkits. It also features a hierarchical, graph-based memory system for efficient management and a specialized toolkit tailored to software engineering tasks. Extensive experiments across three state-of-the-art benchmarks with various backbone models demonstrate the advantages of OpenSage over existing ADKs. We also conduct rigorous ablation studies to demonstrate the effectiveness of our design for each component. We believe OpenSage can pave the way for the next generation of agent development, shifting the focus from human-centered to AI-centered paradigms. Our code is available at https://github.com/opensage-agent/opensage-adk.

Building AI agents today requires human experts to manually design how agents are structured, what tools they use, and how they manage information. This process is time-consuming, limits flexibility, and makes it difficult for agents to adapt to new tasks. We developed OpenSage, a platform that lets AI design its own agents automatically. Instead of relying on humans to define everything upfront, OpenSage allows AI to create specialized sub-agents on the fly, build custom tools as needed, and organize its knowledge using a structured memory system. We tested OpenSage on challenging tasks in cybersecurity, software engineering, and DevOps, and found that agents built with OpenSage consistently outperform those built with existing platforms. Our work represents a shift from human-driven to AI-driven agent design, which could make it much easier to build powerful, adaptable AI assistants in the future.