Operate BashGym training, evaluation, and durable AutoResearch from Codex, Claude Code, Hermes, or another compatible agent. Use for guided campaign preparation and resumption, ML session planning, preflight, goals and KPIs, model training or fine-tuning,…
Generate synthetic training data, manage seeds, preview synthesis jobs, and work with the data factory. Use when asked to generate synthetic data, create training examples, augment a dataset, manage seeds, or check factory job status.
Browse, compare, evaluate, and manage trained models. View leaderboard, trends, lineage, and artifacts. Deploy models to Ollama. Use when asked about models, model comparison, which model is best, model evaluation, deploying a model, or downloading a model.
Check BashGym system status, GPU utilization, hardware info, and aggregate statistics. Use when asked about system health, what's running, GPU usage, memory, disk space, or general system stats.
Browse, promote, demote, classify, and generate training examples from Claude Code execution traces. Use when asked about traces, gold traces, trace counts, promoting or demoting traces, generating examples, exporting training data, or syncing traces.
Operate BashGym training and evaluation runs for Hermes or another configured agent endpoint. Use when launching, monitoring, stopping, classifying, or evaluating SFT, DPO, GRPO/RLVR, Session Distillation, DPPO replay, ECHO/RWML, reward-model, or cascade…
Understand and operate the BashGym ML workspace across datasets, direct LLM training, terminal RL, evaluations, models, artifacts, campaigns, reports, and agent coordination. Use as the stable platform router; load the training or operator skill for…
Read and control I2C and SPI peripherals on Sipeed boards (LicheeRV Nano, MaixCAM, NanoKVM).