Meet Shepherd: An Open-Source Python Substrate That Lets Meta-Agents Fork, Replay, and Revert Any Agent Run
Long-running agents accumulate state that no transcript captures. A coding agent at step 10 holds edited files, a running dev server, installed packages, and a warm prompt cache. When it misreads a traceback and rewrites a file that was already correct, neither available recovery path is cheap: patching forward grows the context and the token bill, and restarting from step one re-pays every model and tool call while reproducing nothing exactly, because runs are non-deterministic. Jumping back to step eight is the option engineers actually want, and it is the one existing runtimes cannot offer. Git versions files, not a live process or a cache. Researchers at Northeastern University and Stanford University have released Shepherd, a Python runtime substrate that records an agent run as a...
Long-running agents accumulate state that no transcript captures. A coding agent at step 10 holds edited files, a running dev server, installed packages, and a warm prompt cache. When it misreads a traceback and rewrites a file that was already correct, neither available recovery path is cheap: patching forward grows the context and the token bill, and restarting from step one re-pays every model and tool call while reproducing nothing exactly, because runs are non-deterministic. Jumping back to step eight is the option engineers actually want, and it is the one existing runtimes cannot offer. Git versions files, not a live process or a cache. Researchers at Northeastern University and Stanford University have released Shepherd, a Python runtime substrate that records an agent run as a Git-like trace of typed events, so any past state can be forked and replayed. The research team reports forks 5× faster than Docker and over 95% prompt-cache reuse on replay. Is it deployable? Yes but it is available in early alpha and not ready for production. Shepherd is MIT-licensed and installable with from PyPI. It needs Python 3.11+. OS-level grant enforcement runs on macOS (Seatbelt) and Linux (Landlock, in a privileged container). Industries: Software engineering and DevOps, AI infrastructure and agent-platform vendors, quantitative finance research, security tooling and offensive-security research, and data engineering. The common trait is not the vertical. It is long-horizon agent runs against heavy sandbox state, where a failed run is expensive to redo. Applications: Live supervision of coding agents, with a meta-agent reverting a bad write before it commits. Automated recovery from a wrong tool call, without a full restart. Branching exploration over candidate agent strategies, compared side by side. Rollout generation for reinforcement learning, forking at selected turns. What Shepherd changes Shepherd is a Python substrate that records an agents execution as a first-clas