Open-source AgnesHarness gives agents dual-system brains, cutting task time 32.9%

量子位 · wechat · 2026-11-20

QbitAI profiles AgnesHarness, an open-source system (Apache 2.0, 2.1k GitHub stars) targeting the biggest cost in enterprise AI agent deployment: while development costs collapsed from 90 units to 1, per-customer adaptation still costs 10.

Key designs:

The system is plugin-based (tools, workflows, skills; MCP integration) and adds MHS, a model-hardware standard connecting agents to arms, sensors, and robots, with physical safety left to device controllers. Self-reported results across 9 benchmarks: 6 first places, 1 tied with Codex, 87.07 on DeepPlanning, 40.69% pass on BigCodeBench-Hard V1.

Original post →

More from coding & agent

coding & agent channel →