agentsclimarketplace

E2b sandboxes

Skill mahmoud20138/Tradecraft/plugins/tradecraft/skills/e2b-sandboxes

E2B open-source cloud sandboxes for executing AI-generated code securely. USE FOR: run code in sandbox, e2b, code interpreter, execute AI code, secure code execution, isolated environment, AI coding agent execution, run untrusted code, cloud sandbox, code execution API, python sandbox cloud, AI agent code runner, safe code execution, jupyter sandbox.From its SKILL.md

Install
npx -y skills add mahmoud20138/Tradecraft --skill e2b-sandboxes

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 18 stars18 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.2 KB, 459 tokens by cl100k_base, as published. Nobody here has run it

E2B Code Interpreter Sandboxes

Secure isolated cloud VMs for executing AI-generated code. Open-source.

Installation

pip install e2b-code-interpreter
npm i @e2b/code-interpreter
export E2B_API_KEY=your_key_here   # get at https://e2b.dev/dashboard

Python Usage

from e2b_code_interpreter import Sandbox

# Basic execution
with Sandbox() as sandbox:
    result = sandbox.run_code("x = 1 + 1; print(x)")
    print(result.logs.stdout)   # ["2"]

# Stateful multi-step session
with Sandbox() as sandbox:
    sandbox.run_code("data = [1, 2, 3]")
    r = sandbox.run_code("print(sum(data))")
    print(r.logs.stdout)        # ["6"]

TypeScript Usage

import { Sandbox } from "@e2b/code-interpreter"

const sandbox = await Sandbox.create()
const result = await sandbox.runCode("print(1 + 1)")
console.log(result.logs.stdout)
await sandbox.kill()

Use With Claude AI Agent

from anthropic import Anthropic
from e2b_code_interpreter import Sandbox

client = Anthropic()
sandbox = Sandbox()

response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Write Python to compute fibonacci(10)"}]
)
code = response.content[0].text
result = sandbox.run_code(code)
print(result.logs.stdout)
sandbox.kill()

Key Features

FeatureDetail
IsolationEach sandbox = fresh cloud VM
StatefulVariables persist within session
LanguagesPython, JavaScript/TypeScript
Outputsstdout, stderr, rich results (plots, tables)
Self-hostableGCP (prod-ready), AWS (in progress), Azure (planned)

Self-Hosting

# GCP (production-ready)
terraform apply -var-file=gcp.tfvars

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 610,677. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.