isanagent

MaxEvolve Triton/PyTorch to JAX/Pallas porting with GpuToJax 12-step pipeline, interpret=True validation, MAP-Elites evolution, and Colab/SSH hardware profiling.

Manage Google Colab sessions and execute code on remote Colab VMs via the colab-cli.

Use when you need to generate a synthetic dataset. You can use Afterimage Python package to create, conversational, tool-calling, multi-choice questions, or other types of structured output datasets for SFT, or preference data for DPO.

Schedule deferred or recurring work via the isanagent cron tool—add/remove jobs with correct runtime context fields.

Configure long wall clocks and use execution_run_background + job polling for ML or hours-long runs without blocking the agent loop.

Run numeric or ML code through isanagent execution tools without flooding context—artifacts, incremental runs, sandbox paths.

Turn papers and docs into a concrete training or evaluation recipe (datasets, metrics, hyperparameters, fine-tuning code).

Checklist before long execution_run or execution_run_background for ML/training scripts.

Out-of-memory and resource pressure recovery without changing the user's training objective.

Interpret Jupyter execution sessions in isanagent—attachments, kernel cwd, tokens; contrast with local provider behavior.

Debug failing scientific Python inside isanagent execution_run—tracebacks, truncation, seeds, provider mismatch.

Author or refine workspace-local skills (SKILL.md) so future turns load concise, agent-oriented procedures.