agent-systems
AI Optimization Framework powered by evolutionary algorithms, multi-armed bandits, and agent societies
Benchmarked agent execution runtime for Python. Sub-10ms cold starts, real-time streaming, time-travel debugging, and self-growing tool libraries. Compare 3 sandbox backends: Docker (OpenSandbox), MicroVM, and in-process AST.
Observability and influence tracing infrastructure for multi-agent AI systems.
Lightweight Agent Framework for building AI apps with any LLM
