SWE-agent
Let a configured language model use repository tools to propose issue fixes.
Overview
What you provide
- A reproducible repository issue, agent configuration and model access
What you get
- A proposed patch and execution trajectory
Setup & workflow
- Follow the official installation and hello-world issue workflow with an isolated environment.
- Prepare the input: A reproducible repository issue, agent configuration and model access.
- Run a small, reversible example and inspect the output: A proposed patch and execution trajectory.
- Review the trajectory and diff and rerun the failing tests before accepting a patch.
Requirements & installation
- Configure the documented runtime and authorized service access before attempting this workflow.
Limits & review
- Maintainers recommend mini-SWE-agent for new work; this listing is the original SWE-agent.
- Evidence review only: the product was not installed or tested in this crawl.
Your part
- Review the trajectory and diff and rerun the failing tests before accepting a patch.
When to consider another product
Unreviewed production decisions, unrestricted account access or guaranteed factual results.
Tasks & use cases1
Fix bugs in an existing project
Task links are limited to the documented workflow. Infrastructure and model components are not treated as ready-made end-user agents.
- Prepare
- A reproducible repository issue, agent configuration and model access
- Get
- A proposed patch and execution trajectory
- Your part
- Review the trajectory and diff and rerun the failing tests before accepting a patch.
Plans & billing details
Cost planning
- Review scope is licensing and documented free-use boundaries, not numeric prices or current hosted-plan allowances.
Published prices are a snapshot. Confirm billing cycle, taxes and current allowances with the provider.
Sources & verification3
This profile is based on official sources, not a hands-on product test.
Vendor descriptions and demos document advertised features. Editorial guidance is based on these sources.
Discovered via OpenFree.Tools.
- SWE-agent — official READMEraw.githubusercontent.com
The maintainer README supports this scope: Let a configured language model use repository tools to propose issue fixes.
- SWE-agent — product entry pointswe-agent.com
The public product entry point was retrieved. Functional scope and setup in this record are grounded in the linked maintainer README.
- SWE-agent — license termsraw.githubusercontent.com
The retrieved license materials support this boundary: MIT. Review the complete terms for your use case.
Frequently asked questions
What does SWE-agent do?
Let a configured language model use repository tools to propose issue fixes.
How much does SWE-agent cost?
Software or published weights are available under MIT. Model inference, external services and your own compute are separate; hosted plan prices were not reviewed.
What should I check before using SWE-agent?
Maintainers recommend mini-SWE-agent for new work; this listing is the original SWE-agent.
