Keyword: rl
- agentdbReleased1 month agoVersion3.0.0-alpha.16
Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1
- simtooreal-cliReleasedyesterdayVersion0.2.1
SimTooReal CLI — AI-powered robotics training platform. Scaffold, train, and deploy robot policies with any AI coding agent via MCP.
- @elizaos/plugin-trajectory-loggerReleasedyesterdayVersion2.0.0-alpha.25
Trajectory logging plugin for ElizaOS - capture agent interaction trajectories for RL training
- @elizaos/robotReleasedyesterdayVersion2.0.11-beta.7
Python robotics stack (MuJoCo sim, Alberta continual-RL training, Brax/MJX baselines, websocket bridge, perception, trajectory DB) with a thin TS surface for re-exports and shared schemas. Drives simulated and real robots via profile-driven configuration;