e2b-code-interpreter
E2B Code Interpreter - Stateful code execution
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 low install friction, uses a permissive license, and provides a clean API for a real security need. Requires an E2B account and API key, and incurs cloud costs; verify pricing and resource limits before committing to production use.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires a valid E2B API key set as the E2B_API_KEY environment variable; sign up at e2b.dev to obtain one.
- Low friction install with a pure Python wheel.
- Active maintenance—last commit 2026-08-13, released 1 day ago.
License · maintenance · safety
MIT (permissive) — MIT license (permissive). You can use, modify, and distribute this package freely in commercial or private projects with minimal restrictions.
last release 2026-08-13 (1 days) · last repo commit 2026-08-13 · 2,377 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 2,640,566 downloads/mo, #2,963 on PyPI
Alternatives
Verify before relying
pip install e2b-code-interpreter
from e2b_code_interpreter import Sandbox
with Sandbox.create() as sandbox:
sandbox.run_code("x = 1")
execution = sandbox.run_code("x+=1; x")
print(execution.text)- Pricing model and cost per sandbox execution or compute time.
- Sandbox resource limits (memory, CPU, execution timeout).
- Supported Python versions inside the sandbox vs. the host interpreter.
- Data residency and compliance certifications for the cloud infrastructure.
What it is and what it does
E2B Code Interpreter is a Python SDK that provisions and controls isolated, stateful code execution environments in E2B's cloud infrastructure. It lets you run Python code—typically generated by LLMs or user input—in a sandbox where each execution preserves state from previous runs, so variables and imports persist across calls. You authenticate with an API key, create a sandbox context, and call run_code() to execute snippets; the sandbox returns execution results including stdout and any errors.
The package is designed for AI workflows where you need to safely execute untrusted or dynamically generated code without risking your local system. It abstracts away sandbox provisioning and lifecycle management, exposing a simple context-manager interface. The underlying e2b dependency handles the cloud communication; httpx manages HTTP requests and attrs provides data structures.
Use it for
- Execute LLM-generated Python code safely in an AI agent or chatbot without running it locally.
- Build interactive notebooks or REPLs where code state persists across user inputs in a cloud sandbox.
- Test or validate user-submitted scripts in a secure, isolated environment before review.
- Run data analysis or math code from untrusted sources without exposing your system.
- Prototype multi-step workflows where intermediate results must carry over between code blocks.
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 low install friction, uses a permissive license, and provides a clean API for a real security need. Requires an E2B account and API key, and incurs cloud costs; verify pricing and resource limits before committing to production use.
Install
e2b-code-interpreter on PyPI
Before you install
Low friction install with a pure Python wheel. Active maintenance—last commit 2026-08-13, released 1 day ago. Supports Python 3.10 through 3.13. Depends on three lightweight runtime packages: httpx, attrs, and e2b.
Requires a valid E2B API key set as the E2B_API_KEY environment variable; sign up at e2b.dev to obtain one.
License in practice
MIT license (permissive). You can use, modify, and distribute this package freely in commercial or private projects with minimal restrictions.
Quickstart
pip install e2b-code-interpreter
from e2b_code_interpreter import Sandbox
with Sandbox.create() as sandbox:
sandbox.run_code("x = 1")
execution = sandbox.run_code("x+=1; x")
print(execution.text)Verify before relying
- Pricing model and cost per sandbox execution or compute time.
- Sandbox resource limits (memory, CPU, execution timeout).
- Supported Python versions inside the sandbox vs. the host interpreter.
- Data residency and compliance certifications for the cloud infrastructure.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release <4.0,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 3 packageshttpxattrse2b |
| Maintenance | Actively maintained 1 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 2,640,566 / month, #2,963 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13 |
Evidence: e2b_code_interpreter-2.9.1-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 › “execute code in sandbox”
- e2b-code-interpreterRuns AI-generated or arbitrary Python code in isolated cloud…
- agent-sandboxA Python SDK for accessing sandbox, shell, file, Jupyter, Node.js,…
- langchain-daytonaIntegrates Daytona sandboxes with LangChain's Deep Agents framework,…
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 · e2b-desktop · llm-sandbox · hyperlight-sandbox · opensandbox · daytona · prime-sandboxes · koyeb-sdk · pydantic-monty-runtime · lightning-sdk