Agent Sandboxesagentsandboxes.org
Sandbox profile · Open-source project

SWE-ReX

Answer in brief

Runtime interface from the SWE-agent team for running agent shell sessions locally or in Docker, Modal and AWS Fargate sandboxes, built for massively parallel runs. A thin, backend-agnostic shell runtime that is most useful when the goal is parallel coding-agent evaluation rather than a hosted sandbox.

By the Agent Sandboxes editors · Updated

Overview

SWE-ReX is "a runtime interface for interacting with sandboxed shell environments" that came out of the SWE-agent project. A Deployment starts the environment (Docker/Podman, Modal, AWS Fargate, a remote host or the local machine), a FastAPI server inside it executes commands, and the Python client gets a RemoteRuntime with the same interface as the local runtime. It recognises when commands finish, returns output and exit codes, supports interactive tools such as ipython and gdb, and keeps several shell sessions open at once.

The README claims "Running 100 agents in parallel? No problem either!" and demos 30 SWE-bench instances at once; Daytona support is marked "(WIP)". MIT-licensed, pip install swe-rex with extras for Modal and Fargate; no version or release status is stated in the docs.

Notable

  • Backends: local, Docker/Podman, Modal, AWS Fargate, remote; Daytona marked "(WIP)"
  • README claims "fast, massively parallel agent runs" and shows 30 SWE-bench instances in parallel
  • MIT licence; FastAPI server inside each environment

SWE-ReX specifications

AttributeDetails
IsolationDepends on the deployment: Docker or Podman container (DockerDeployment), Modal or AWS Fargate (ModalDeployment, FargateDeployment), a remote host, or no isolation with LocalDeployment; a FastAPI server inside the environment relays commands
DeploymentOpen-source project · Self-hostable
Open sourceYes (MIT)
SDKs and interfacesPython, REST API
Cold start (vendor claim)Not documented
Max session lengthNot documented
PersistenceMultiple interactive shell sessions stay open for the life of the deployment; file read/write through the runtime; no snapshot or persistence beyond the deployment documented
GPUNot documented
NetworkingThe container runtime server listens on port 8000, mapped to a free host port; other deployments expose the server over HTTP; network policy is not documented
PricingFree (MIT); Modal and Fargate backends are billed by those providers
Free tierFree to self-host
ComplianceNot documented
RegionsNot documented

Facts from SWE-ReX’s public documentation, verified November 9, 2026. Performance numbers are vendor claims.

Strengths and trade-offs

Strengths

  • You run SWE-agent or similar and want to swap execution backends without changing agent code
  • You need many parallel shell sessions for benchmark evaluation
  • You want to run on Modal or Fargate without writing provider-specific glue

Trade-offs

  • Isolation is whatever the chosen backend provides; LocalDeployment has none
  • No snapshots, persistence or network policy documented
  • No stated release status; oriented towards research evaluation workflows

Good fit for: Running many SWE-agent-style shell sessions in parallel across local, Docker, Modal or Fargate backends.

Use cases SWE-ReX fits

  • RL & evals: Open-source runtime for running many SWE-agent-style shell sessions in parallel across local, Docker, Modal or Fargate backends.

How SWE-ReX compares

SandboxIsolationOpen sourceSelf-host / BYOCCold start (vendor)Max sessionSnapshots / pauseGPUSDKs
SWE-ReXDocker / Modal / FargateYesYes / NoNot documentedNot documentedNo / Not documentedNot documentedPython, REST API
OpenHands RuntimeDocker containerYesYes / NoNot documentedNot documentedNot documented / Not documentedNot documentedPython, JavaScript/TypeScript, REST API
LLM SandboxDocker/Podman/K8s containerYesYes / NoNot documentedNot documentedNo / Not documentedNot documentedPython, MCP server
Modal SandboxesgVisor or VMNoNo / Not documented<1 sUp to 24 hYes / YesYesPython, JavaScript/TypeScript, Go
DaytonaContainers or VMsNoNot documented / Yes<90 msUnlimitedYes / YesYesPython, TypeScript, Ruby, Go, Java
Docker SandboxesMicroVMNoYes / NoNot documentedUntil removed (local)Yes / YesYessbx CLI, TypeScript (cloud), REST API (cloud)
Prime SandboxesmicroVM, own kernelNoNo / NoNot documented60 min default, unlimitedYes / YesNoPython, CLI, REST API

See all SWE-ReX alternatives →

Frequently asked questions

What is SWE-ReX?
Runtime interface from the SWE-agent team for running agent shell sessions locally or in Docker, Modal and AWS Fargate sandboxes, built for massively parallel runs. A thin, backend-agnostic shell runtime that is most useful when the goal is parallel coding-agent evaluation rather than a hosted sandbox.
How does SWE-ReX isolate code?
SWE-ReX documents its isolation as: Depends on the deployment: Docker or Podman container (DockerDeployment), Modal or AWS Fargate (ModalDeployment, FargateDeployment), a remote host, or no isolation with LocalDeployment; a FastAPI server inside the environment relays commands.
Is SWE-ReX open source?
Yes (MIT). It can be self-hosted.
How much does SWE-ReX cost?
Free (MIT); Modal and Fargate backends are billed by those providers Check the official pricing page for current rates.
What are the alternatives to SWE-ReX?

Sources

  1. github.com/SWE-agent/SWE-ReX
  2. swe-rex.com/latest/
  3. swe-rex.com/latest/architecture/
  4. swe-rex.com/latest/api/deployments/docker/

Cite this page

Agent Sandboxes. (2026). SWE-ReX. agentsandboxes.org. Last reviewed November 9, 2026. https://agentsandboxes.org/sandboxes/swe-rex/

Found an error or a missing sandbox? Submit a correction — every entry links to the sources it relies on.