e2b
E2B SDK that give agents cloud environments
Decision gist · record as of 2026-08-14
Yes, if you need to execute untrusted or AI-generated code safely. The package is actively maintained, has no known vulnerabilities, uses a permissive MIT license, and offers low install friction. The main commitment is the E2B API dependency—you'll need to sign up for the service and manage an API key. For applications that don't require remote code execution or sandboxing, it's unnecessary overhead.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python >=3.10 and a valid E2B_API_KEY environment variable set with credentials from https://e2b.dev.
- Low install friction with a pure-Python wheel and 12 runtime dependencies.
- The project is actively maintained with a recent commit on 2026-08-13 and shows strong community adoption at top_5000 tier.
License · maintenance · safety
MIT (permissive) — MIT license permits commercial and private use with minimal restrictions, making it suitable for most production and research applications.
last release 2026-08-13 (1 days) · last repo commit 2026-08-13 · 13,404 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 5,805,113 downloads/mo, #2,034 on PyPI
Alternatives
Verify before relying
pip install e2b
from e2b import Sandbox
with Sandbox.create() as sandbox:
result = sandbox.commands.run('echo "Hello from E2B!"')
print(result.stdout)- Whether the 12 runtime dependencies introduce any transitive security concerns beyond the zero known vulnerabilities in e2b itself.
- Pricing model and rate limits for sandbox creation and execution time.
- Performance characteristics and latency for sandbox startup and command execution.
What it is and what it does
E2B is a Python SDK that lets you spawn and manage isolated cloud sandboxes for executing code that you don't fully trust—typically AI-generated code from language models or user submissions. It abstracts away the complexity of provisioning secure environments and provides a simple API to run shell commands or Python code inside those sandboxes, with results streamed back to your application.
The package is designed for AI agents and applications that need to safely execute untrusted code without risking the host system. It handles the infrastructure side (sandbox provisioning, isolation, cleanup) and exposes a straightforward interface: create a sandbox context, run commands or code, and capture output. The SDK requires an API key from the E2B service and modern Python (3.10+), and pulls in a moderate set of dependencies including httpx for HTTP communication, protobuf for serialization, and rich for output formatting.
Use it for
- Run AI-generated code from language models in isolation to prevent malicious or buggy code from affecting your application.
- Build AI agent systems that need to execute user-submitted scripts or formulas safely in a cloud environment.
- Test untrusted third-party code or plugins without risking your local machine or production infrastructure.
- Provide a secure code execution backend for collaborative tools or notebooks where users can run arbitrary Python.
- Prototype and validate AI-generated solutions (data analysis, automation scripts) before deploying them to production.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need to execute untrusted or AI-generated code safely.
The package is actively maintained, has no known vulnerabilities, uses a permissive MIT license, and offers low install friction. The main commitment is the E2B API dependency—you'll need to sign up for the service and manage an API key. For applications that don't require remote code execution or sandboxing, it's unnecessary overhead.
Install
e2b on PyPI
Before you install
Low install friction with a pure-Python wheel and 12 runtime dependencies. The project is actively maintained with a recent commit on 2026-08-13 and shows strong community adoption at top_5000 tier.
Requires Python >=3.10 and a valid E2B_API_KEY environment variable set with credentials from https://e2b.dev.
License in practice
MIT license permits commercial and private use with minimal restrictions, making it suitable for most production and research applications.
Quickstart
pip install e2b
from e2b import Sandbox
with Sandbox.create() as sandbox:
result = sandbox.commands.run('echo "Hello from E2B!"')
print(result.stdout)Verify before relying
- Whether the 12 runtime dependencies introduce any transitive security concerns beyond the zero known vulnerabilities in e2b itself.
- Pricing model and rate limits for sandbox creation and execution time.
- Performance characteristics and latency for sandbox startup and command execution.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 12 packagespython-dateutilwcmatchprotobuf-pyhttpxh2attrspackagingtyping-extensionsdockerfile-parserichconnectrpcpyqwest |
| Maintenance | Actively maintained 1 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 5,805,113 / month, #2,034 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: e2b-2.39.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “run untrusted code safely”
- e2bE2B provides a Python SDK to create and control isolated cloud…
- daytonaDaytona is a Python SDK for managing and interacting with sandboxed…
- starlark-pyo3Exposes the Starlark interpreter (a Python-like language) to Python…
Give your agent the search over MCP, or paste the wish link into any chat.
More Distributed Computing packages
gRPC Python is an HTTP/2-based RPC framework that enables you to define and call remote procedures across network boundaries using protocol buffers for serialization.
Install it if you need RPC communication in a distributed system or are integrating with existing gRPC services.
execnet lets you spawn and communicate with Python interpreters across local processes, remote hosts, and different platforms, using a simple API for task distribution and inter-process messaging.
However, the aging maintenance status (275 days since last release) means you should verify it meets your concurrency and performance needs before committing to a…
Cloudpickle extends Python's standard pickle module to serialize lambda functions, interactively-defined functions and classes, and other constructs that the default pickle cannot handle, making it suitable for cluster computing and remote code execution.
Install it if you need to serialize lambda functions, interactively-defined code, or non-standard Python constructs for cluster computing or distributed execution.
Provides a unified, open()-compatible Python API for streaming large files from remote storage (S3, GCS, Azure, HDFS, SFTP, HTTP) and local filesystems, with transparent compression support.
Install it if you work with large files on cloud storage or remote systems and want to avoid writing boilerplate around multiple SDKs.
Portalocker provides cross-platform file locking with support for exclusive and shared locks, plus Redis-based distributed locks and process-aware PID file locking.
Install it if you need file or process coordination; the optional extras (pywin32, redis) are only required for specific lock types.
Ray is a distributed computing framework that scales Python applications from a single machine to multi-node clusters, providing abstractions for parallel tasks, stateful actors, and shared objects.
See also e2b-code-interpreter · e2b-desktop · opensandbox · koyeb-sdk · llm-sandbox · starlark-pyo3 · hyperlight-sandbox · prime-sandboxes · RestrictedPython · blaxel