Quarq

Popular repositories Loading

1. argus argus Public

   A recursive evidence-gated cognitive runtime for memory-native AI agents, combining hybrid retrieval, temporal reasoning, async learning, and plug-and-play tools.

   Python 277 25

2. roboeval roboeval Public

   Local SDK for repeatable robot policy evals, debugging, regression detection, and structured reports across simulators, scenarios, and policy versions.

   Python 8

3. benchmarks benchmarks Public

   LongMemEval-S benchmark runner for Quarq Agent. Feeds conversation history into a running agent-oss FastAPI server, asks benchmark questions, judges responses, and writes resumable local reports.

   Python 3