Agnes Harness open-sources dual-system agent architecture
Agnes Harness is an Apache 2.0-licensed open-source agent system that pairs a 9B Agnes Sys1.0 model for fast decisions with a large language model for complex reasoning. Its test-time training and recursive self-improvement mechanisms adapt to new tasks and turn validated procedures into reusable Playbooks. Plugins, MCP connectivity and the Model Hardware Standard are designed to integrate software systems and physical devices. Developer-reported tests cited by QbitAI showed up to 14.3 times faster decisions, about one-twenty-seventh of the per-call cost and a 32.9% reduction in total task time in a robot-dog simulation. No independent evaluation was identified in the supplied report.
The release offers an open-source architecture that combines rapid decision-making, task adaptation, reusable experience and hardware integration, potentially serving as a reference for developers building agents that connect business software with physical devices. Its reported speed and cost benefits remain developer-test results without identified independent validation.
双系统决策+双层自进化,Agnes让Agent效率最高提速14倍,成本骤降至1/27! – 量子位
< img id="wx_img" src="https://www.qbitai.com/wp-content/uploads/imgs/qbitai-logo-1.png" width="400" height="400">
双系统决策+双层自进化,Agnes让Agent效率最高提速14倍,成本骤降至1/27!

已开源Agnes Harness