AI 服务暂时不可用，以下为来源正文，待恢复后补全翻译。
Rapid self-improvement for your hardware algorithms. Use large-scale AI agent teams to rapidly discover code improvements on your hardware systems. $curl -fsSL https://onyxresearch.ai/install.sh | bash Platform sign in Agent teams that research with you. With one command, point Onyx at your codebase and have full control over a parallel agent team to rapidly improve any metric. 1 Install Onyx for your Claude, Codex, or OpenCode. One-line install for the Onyx agent and CLI: $curl -fsSL https://onyxresearch.ai/install.sh | bash 2 Run /onyx inside your codebase. Experiments as code. Onyx uses Git in your existing code to experiment, so your compounding results are seamlessly tracked and ready to be pulled in. Run Onyx agents anywhere. Use your same tools Keep your existing repositories, simulators, and hardware testing workflows. Simply point Onyx at your problems. drone_sim/ quad_dynamics.py rotor_thrust_model.py /onyx improve rotor thrust model hover_eval.py Git experiment tracking Onyx experiments are simply Git code commits with stored metric data, making your development seamless. ExperimentNameMetricStatus a3f92cStiffer rear damping0.913Succeeded 7c48beLongitudinal slip term0.897Succeeded e91d07Thermal derating map0.874Succeeded 52b6f9Anti-windup clamp0.869Succeeded c07a31Regen torque blend0.841Succeeded 91f4d2Lookahead gain sweep0.828Succeeded Shared team knowledge graph Every experiment across your whole team becomes durable, compounding knowledge. Breakthroughs transfer across your hardware systems and teammates share learnings. Project DB Research /onyx find new physics terms for the tire model c7d3a1erefine loss mask 4b09f2aadjust lr warmup 9e51c08rebalance dataset TL Research /onyx tune the powertrain control system 2f8b6c1smooth control output a41d9e7clip grad norm 6c03b5fbump eval episodes Improve your hardware in minutes. No tutorial needed, just ask the Onyx agent to help you get started. $curl -fsSL https://onyxresearch.ai/install.sh | bash Platform sign inBook a meeting