AgentOS: a Rust runtime for AI agents with deterministic time-travel replay

Developer Wahib El Khadiri has released AgentOS, an open-source Rust runtime for AI agents that provides deterministic time-travel replay. The runtime journals every LLM exchange and tool result, enabling offline replay and forking into alternate timelines without API costs. AgentOS sits underneath frameworks like LangGraph and AutoGen, offering supervision, health endpoints, and a debugging dashboard.

Most agent frameworks help you build a workflow. The harder part starts after that: the workflow has to run as a long-lived process, fail clearly, restart carefully, and be inspectable after the fact. That's the gap I'm building AgentOS for — an open-source, Rust-first runtime layer that sits underneath frameworks like LangGraph, AutoGen or CrewAI instead of replacing them. cargo run -p agentos-cli -- run --agent examples/simple agent.toml That single command brings up a supervised agent, a health endpoint, a gRPC message bus, a live SSE event stream, and a recorded trace you can replay later. No API key is needed just to bring the runtime up. Your agent does something weird on step 7. Reproducing it costs real API calls, and it never behaves the same way twice. AgentOS journals every LLM exchange and tool result at the provider boundary, so any run can be replayed deterministically — and forked into alternate timelines: agentOS run --agent my agent.toml every step journaled automatically agentOS replay --session agent 123 offline re-run, no API cost, drift-checked agentOS fork --from ckpt 4 --prompt "try the other path" The dashboard's Recordings view turns those journals into a scrubbable timeline: step through the prompt, each exchange, tool calls and their results, with per-exchange checkpoints as fork anchors. crates/kernel — lifecycle, agent handles, supervisor crates/bus — in-memory, gRPC, SSE and WebSocket messaging crates/trace — recording, replay, diff, checkpoint model crates/vault — secret isolation, encryption, scopes, audit crates/memory , crates/registry , crates/llm , crates/cli , crates/sdk dashboard/ — React debugging surfaceStable enough for local use: the run / ps / logs / trace / replay CLI flows, local state inspection, export and import, and the core crates with workspace checks and tests. Still experimental: the dashboard, the WASM plugin runtime, Docker Compose packaging, LLM provider integrations, and Python/TypeScript SDK packaging. Stronger restart and recovery guarantees with explicit tests are next. It is an alpha, and I would rather say that than claim production hardening it has not earned yet. git clone https://github.com/WAHIB-EL-KHADIRI/AgentOS cd AgentOS cargo build --workspace cargo run -p agentos-cli -- run --agent examples/simple agent.toml Repo: https://github.com/WAHIB-EL-KHADIRI/AgentOS https://github.com/WAHIB-EL-KHADIRI/AgentOS Feedback on the runtime boundaries is what I want most: if you run agents today, what breaks first for you — supervision, observability, or reproducing failures?