xpu liveBETA
Agents›SWE-agent

SWE-agent is an AI agent project from Princeton and Stanford researchers in the xpu live directory. This profile brings together its recorded features, deployment options and official sources. Use it to compare the agent software with other tools and understand the model access and setup it requires.

A research-oriented software-engineering agent that uses tools to investigate and fix repository issues. Its configuration and execution traces support experimentation with autonomous coding systems.

SWE-agent features and use cases

SWE-agent is listed under Coding, Research. Recorded interfaces include CLI. The feature and use-case sections describe the documented scope; they do not guarantee that every workflow runs without configuration or review.

Match the agent to a representative task before extending it to a larger workflow. Check the tools it needs, the files or services it accesses and the expected outputs. An agent is an application that coordinates model calls and tools; it is separate from the underlying language model.

SWE-agent models and deployment

The model compatibility section records the supported provider routes and configuration details from the project references. Verify the intended model endpoint and request format in SWE-agent documentation. Different models can behave differently even when the same agent workflow is used.

Review where the software runs and how its tools are connected. Local, container and hosted deployment options can require different runtimes and account settings. The saved implementation languages and deployment notes provide a starting point, while the official installation instructions describe the current requirements.

When evaluating SWE-agent, test the workflow with your own prompts and files. Inspect generated changes and tool results before relying on them. Longer tasks can make multiple model calls, so latency and cost depend on the chosen model and the steps the agent takes.

Software license and operating costs

SWE-agent has MIT recorded as its agent software license. Review the license source for the applicable terms. An open-source agent license does not automatically cover connected models, external tools or hosted services.

Read the cost model beside the deployment details. Model inference, hosting and external integrations may create separate charges. Estimate usage across a complete task rather than treating one prompt as the entire workflow. Repeated attempts, long context and tool responses can affect the total billed volume.

SWE-agent project status and sources

The catalog records the project status as Superseded, with sources checked on 2026-09-28. Review the limitations and any successor link when a project is in beta, superseded or no longer maintained. A saved status is a dated catalog observation, so check current releases before installing.

Consult SWE-agent official project repository for the source code and release information. This profile keeps specifications separate from assumptions: missing details remain unknown until a reference confirms them.

Compare other AI agents, explore AI API providers and review model rankings and pricing. Choose SWE-agent when its documented interfaces, deployment requirements and operating model fit the task you want to carry out.

CodingResearch

What it can do

  • Automatic investigation of GitHub issues
  • Configurable tool-based agent workflows
  • YAML-based configuration
  • Research and evaluation workflows

Where it fits

  • Software-engineering agent research
  • Studying automated issue resolution
  • Reproducing existing SWE-agent workflows

Models & deployment

Model compatibility

Configurable language models; see the repository configuration and documentation.

Where it runs

Configured development environment with tool execution

Cost model

Open-source software. Model inference, hosting and external tools may cost extra.

Limitations & scope

The maintainers recommend mini-swe-agent for new work and state that it has superseded SWE-agent. This profile preserves the original project as a distinct entry.