Overview
OpenSage is a self-contained ecosystem for building next-generation AI systems that can self-evolve. It consists of four core components that together enable an end-to-end pipeline for agent construction, deployment, training, and inference.
- OpenSage-ADK: An AI-centric Agent Development Kit that enables AI to self-create agent topologies and synthesize toolsets, rather than relying on hand-crafted agent designs.
- OpenSage-Inference: AGInfer, an LLM inference engine optimized for agentic tasks, featuring long-context and tool-calling support with a modular design for high extensibility across new model architectures.
- OpenSage-Training: A framework for large-scale agentic RL training with seamless integration into popular training frameworks such as AReaL and SLIME, built on the OpenSage agent scaffold and environment infrastructure.
- OpenSage-Env: Integrated with popular environment frameworks (e.g., OpenEnv), with all agent execution running on NitroBox — an OpenSage-developed sandbox environment designed for efficient agentic RL training.
OpenSage Architecture
End-to-end pipeline: environment → rollout → training
- Connect to many envs (AgentBeats)
- OpenSage auto env generation
- NitroBox: lightweight Docker
- AI-centric agent topology generation
- AI-centric tool creation
- Comprehensive memory system
Rollout Collection (OpenSage-eval layer)
Agent interacts with env; collects trajectories + rewards
Training Framework (veRL, SLIME, AReaL, etc.)
Highlights
OpenSage-ADK
SageAgent, built by AI itself using OpenSage-ADK, significantly outperforms other open-source agents and achieves state-of-the-art results across software engineering and cybersecurity benchmarks.
SageCTF
Built on OpenSage, SageCTF competed solo at DEF CON CTF 2026 — recovering 8 flags across 7 of the world's hardest challenges, placing in the top 5% of teams, and outscoring every No-AI and Low-AI team. Read the full story.