Tool overview
SWE-ReX is listed under Programming AI tools.
What is SWE-ReX?
SWE-ReX is an MIT-licensed runtime interface that lets AI agents execute shell commands in isolated local or remote environments. It supports Docker, Modal, AWS Fargate, and extensible runtime backends for parallel software-engineering work.
Best for
Research and engineering teams running coding agents in isolated environments
Who is it for?
Decision note
Rebuilt from the original export under the complete V411 factual-source-verification workflow. Preview only. Apply remains blocked until Failures = 0, Warnings = 0, Unmapped = 0, Missing = 0; explicit clears are reviewed; image import is disabled or V380 accepts the asset; a representative WordPress edit screen is compared with the export and proposed row; and a post-Apply zero-change Preview succeeds.
Key features
Unified runtime interface for sandboxed shell execution
Local Docker and remote cloud backends
Modal and AWS Fargate optional support
Parallel environments for agent evaluation
Use cases
Run coding agents against repositories
Create isolated test environments
Execute benchmark jobs in parallel
Develop custom remote runtime backends
Pros
- MIT-licensed and openly maintained
- Local and cloud runtime choices
- Designed for large parallel workloads
Limitations
Agents can run destructive commands, expose secrets, or incur cloud cost when isolation is incomplete.
Use disposable environments, least privilege, network controls, quotas, audit logs, and human approval for sensitive operations.
Pricing details
Billing options
Pricing note
SWE-ReX is free under MIT. Users pay their own Docker, Modal, AWS, or other infrastructure costs. No managed subscription price is published.
Supported programming languages
- English
Integrations
Docker
Modal
AWS Fargate
Daytona work in progress
Please log in to join the discussion.