# SWE-ReX

> Runtime interface for coding agents to interact with persistent shell sessions across local and remote sandbox environments.

- id: `swe-rex`
- category: Infrastructure (`infrastructure`)
- url: https://github.com/SWE-agent/SWE-ReX
- repo: https://github.com/SWE-agent/SWE-ReX
- status: active
- pricing: open-source
- license: MIT
- tags: sandbox, shell, coding-agents, python
- auth: none
- access notes: Local Python package: pip install swe-rex. Optional backend credentials and infrastructure are configured separately.
- related: SWE-agent (https://indexagentica.com/entries/swe-agent/); mini-swe-agent (https://indexagentica.com/entries/mini-swe-agent/)
- sources: https://github.com/SWE-agent/SWE-ReX , https://github.com/SWE-agent/SWE-ReX/blob/main/LICENSE.txt , https://pypi.org/project/swe-rex/
- added: 2026-11-08
- updated: 2026-11-08
- last verified: 2026-11-08
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/swe-rex/
- json: https://indexagentica.com/api/entries/swe-rex.json

Install swe-rex from PyPI (1.4.0; Python 3.10+). Detects command completion and returns output/exit status, supports interactive command-line tools and multiple shell sessions. Separates agent logic from execution backends such as local hosts, Docker, Modal and AWS; extras include modal and fargate. MIT software; hosted infrastructure and model use are separate. It permits arbitrary commands in the configured environment, so isolation and permissions remain deployment responsibilities.
