Skip to content
BYOK Tools

SWE-agent

Research agent that fixes GitHub issues autonomously.

3.9 editor score•Coding Agents & IDEs•Free & open source

Overview

SWE-agent from Princeton and Stanford turns an LLM into an agent that can resolve real GitHub issues using a custom agent-computer interface. It is configurable with your own model keys via LiteLLM.

  • Issue-to-PR automation
  • Agent-computer interface
  • Configurable via YAML
  • Benchmark tooling

Our verdict

What we like

  • Strong research pedigree
  • Fully configurable

Watch out for

  • Aimed at researchers more than daily use

Works with these providers

Keys from these providers work in this app. Usage is billed by the provider at its list price.

BYOK Key Safety Score

Key handling in SWE-agent

How we score
100/ 100

Grade A

Your key is stored on your device and requests go directly to the provider.

  • Key storage

    Key stays on your device; requests go direct to the provider.

    40/40
  • Auditable code

    Open source: anyone can verify how keys are handled.

    25/25
  • Self-hosting

    Can run entirely on your own infrastructure.

    15/15
  • Offline option

    Supports local models, so no key is needed at all for private work.

    10/10
  • Provider choice

    6 provider options, which lets you pick the provider whose data terms you trust.

    10/10

Whatever the score, give each app its own key, set a monthly spend limit with your provider, and revoke keys you no longer use. Read the key-safety checklist.

SWE-agent FAQ

Does SWE-agent support bring your own key?
Yes. SWE-agent accepts your own API key from OpenAI, Anthropic, Google Gemini, OpenRouter, Ollama and OpenAI-compatible. Usage is billed by the provider at its API rates.
Where does SWE-agent store my API key?
On your device. Requests go directly from SWE-agent to the provider. Its BYOK Tools Key Safety Score is 100/100.
Is SWE-agent free?
Open source: Free & open source. API usage is billed separately by your model provider.
Is SWE-agent open source?
Yes. The source code is at https://github.com/SWE-agent/SWE-agent. It can also be self-hosted.
Can SWE-agent run local models?
Yes. It can connect to local runtimes such as Ollama or LM Studio, so no API key is needed for private or offline use.
Which platforms does SWE-agent support?
CLI, Self-hosted.

Community reviews

No reviews yet.