From togetherai-skills
Executes Python remotely in managed Together AI sandboxes with stateful sessions, file uploads, data analysis, chart generation, and notebook-like runs. Use for remote execution over local, clusters, or model hosting.
npx claudepluginhub togethercomputer/skillsThis skill uses the workspace's default tool permissions.
Use Together Sandboxes when the user wants to execute Python remotely in a managed sandbox.
Enables secure execution of untrusted Python/Node.js code, git operations, and scripts in persistent Linux containers on Cloudflare edge using Workers SDK.
Builds secure code execution sandboxes on Cloudflare Workers with Sandbox SDK. Handles commands, Python/JS/TS interpreters, files, ports; prefers Cloudflare docs retrieval.
Guides hosted agent infrastructure for remote sandboxes, pre-built images, snapshots, multiplayer collaboration, and scalable background execution beyond local limits.
Share bugs, ideas, or general feedback.
Use Together Sandboxes when the user wants to execute Python remotely in a managed sandbox.
Typical fits:
together-gpu-clusters for full infrastructure control or larger distributed jobstogether-dedicated-containers for custom containerized runtime logictogether-chat-completions if the user only wants generated code, not executed codeclient.code_interpreter.execute().session_id when the workflow depends on prior state.stdout, stderr, structured outputs, and display outputs separately.together>=2.0.0). If the user is on an older version, they must upgrade first: uv pip install --upgrade "together>=2.0.0".session_id as part of the workflow state.response.errors before assuming a run succeeded.plt.show() with the Agg backend does not reliably produce display_data outputs. To retrieve charts, save the figure to a BytesIO buffer with fig.savefig(), base64-encode it, and print the encoded string to stdout. Parse it from the stdout output on the client side. See the chart example in scripts/execute_with_session.py.