ml-agent-orchestrator is a Python package that provides a closed-loop automated ML experiment engine. It uses Claude Code as an editor and Google Antigravity CLI as an evaluator, with git-based state decisions, persistent agent sessions, context-rotation memory, an AST code graph, and a temporal experiment knowledge graph. It is designed for ML researchers and engineers who want to automate and systematically track their experimentation workflow.
ml-agent-orchestrator sits in PulseGate's Autonomous agents & workflows category. Manually managing, tracking, and iterating on machine learning experiments at scale. ml-agent-orchestrator is an open-source project aimed at machine learning engineers. The project is open source (MIT). ml-agent-orchestrator is available on the command line.
It is developed by 1to3for5vi7ate9x, and the product first shipped in 2026. The project is developed in the open on GitHub with 3 commits in the last 90 days. Among its 5 catalogued features are closed-loop experimentation, git-based state, and persistent agent sessions.
Latest indexed changes and source events
ml-agent-orchestrator verified by the PulseGate indexer
Other apps tracked under the same category.
