The agent loop, embodied. Tool-using runtime + fail-closed safety pipeline + sim-first execution + statistically-rigorous bench harness + post-hoc analysis (counterfactual replay, causal attribution, LLM judge, property mining) for embodied AI. Sister project to GhostLM.
agent robotics mcp stl safety causal-inference vla gymnasium ros2 mujoco counterfactual sim2real tool-use safe-rl embodied-ai policy-gates constrained-mdp sim-first property-mining ghostloop
-
Updated
May 10, 2026 - Python