AgentOS - Runtime Infrastructure for AI Agents
AgentOS is an open-source runtime layer for AI agents. It focuses on the infrastructure around agents: lifecycle, supervision, messaging, state, secrets observability, and trace replay.
Created by WAHIB EL KHADIRI — founder and architect.
Most agent frameworks help you build an agent workflow. AgentOS focuses on what happens after that workflow needs to run as a long-lived process, fail clearly restart carefully, and be inspected after the fact.
See it run
Real output from a fresh clone — no API key required to bring the runtime up:
$ cargo run -p agentos-cli -- run --agent examples/simple_agent.toml
INFO agentos_kernel::supervisor: agent spawned and running agent_id=agent_simple_agent state=Running name=simple-agent
INFO agentos_kernel::agent: agent loop started agent_id=agent_simple_agent
INFO agentos_kernel::events: system event emitted event=agent.spawned seq=0
INFO agentOS::run: AgentOS runtime started agent_id=agent_simple_agent host=127.0.0.1 http_port=8080 grpc_port=50051 sse_port=8081
INFO agentos_kernel::health: health server listening on 127.0.0.1:8080
INFO agentos_bus::grpc: gRPC bus server listening on 127.0.0.1:50051