AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Together Sandboxes

skill-togethercomputer-skills-together-sandboxes · by togethercomputer

Remote Python execution in managed sandboxes on Together AI with stateful sessions, file uploads, data analysis, chart generation, and notebook-like runs via the Sandboxes API. Reach for it whenever the user wants managed remote Python execution instead of local execution, raw clusters, or full model hosting.

↗ Repository
— No reviews yet
0 installs
30 views
0.0% view→install

Install

$ agentstack add skill-togethercomputer-skills-together-sandboxes

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-togethercomputer-skills-together-sandboxes)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Together Sandboxes? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Together Sandboxes

Overview

Use Together Sandboxes when the user wants to execute Python remotely in a managed sandbox.

Typical fits:

  • stateful Python sessions
  • data analysis and chart generation
  • agent-generated code execution
  • file uploads into a remote runtime

When This Skill Wins

  • The user wants remote execution rather than local shell execution
  • Session state needs to persist across multiple calls
  • The result may include display outputs such as charts
  • A lightweight managed runtime is enough; no custom infra is required

Hand Off To Another Skill

  • Use together-gpu-clusters for full infrastructure control or larger distributed jobs
  • Use together-dedicated-containers for custom containerized runtime logic
  • Use together-chat-completions if the user only wants generated code, not executed code

Quick Routing

  • Remote execution with session reuse
  • Start with [scripts/executewithsession.py](scripts/executewithsession.py) or [scripts/executewithsession.ts](scripts/executewithsession.ts)
  • Response schema and session listing
  • Read [references/api-reference.md](references/api-reference.md)
  • MCP-style access for agent workflows
  • Read [references/api-reference.md](references/api-reference.md)

Workflow

  1. Decide whether the task needs code execution or only code generation.
  2. Start a session with client.code_interpreter.execute().
  3. Reuse session_id when the workflow depends on prior state.
  4. Inspect stdout, stderr, structured outputs, and display outputs separately.
  5. List sessions only when the user needs operational visibility or cleanup.

High-Signal Rules

  • Python scripts require the Together v2 SDK (together>=2.0.0). If the user is on an older version, they must upgrade first: uv pip install --upgrade "together>=2.0.0".
  • Treat session_id as part of the workflow state.
  • Inspect 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/executewithsession.py](scripts/executewithsession.py).
  • Use this skill when the user benefits from remote stateful execution, not just because Python is involved.
  • If the task outgrows the sandbox model, hand off to GPU clusters or dedicated containers.

Resource Map

  • API reference: [references/api-reference.md](references/api-reference.md)
  • Alternative access patterns: [references/api-reference.md](references/api-reference.md)
  • Python workflow: [scripts/executewithsession.py](scripts/executewithsession.py)
  • TypeScript workflow: [scripts/executewithsession.ts](scripts/executewithsession.ts)

Official Docs

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills