SWE-agent: review, pricing, security and alternatives

What SWE-agent does

SWE-agent belongs to the coding agents family: they read a repository, edit files, run the tests and fix things until everything passes, in a terminal or an editor. On our grid it ranks #41 of the 74 projects of this family listed in the directory.

You use it from: terminal (CLI). Usable models: Claude (Anthropic), GPT (OpenAI), Gemini (Google), local models (Ollama, llama.cpp, vLLM…), and any OpenAI-compatible model. It can run on your own machine or server.

Who is SWE-agent for?

It is aimed at developers and technical teams who want to hand off part of the work on their codebase while keeping the final review. Typical tasks people give it:

• fix a bug from an issue or an error message
• write or extend tests
• migrate code to a new library version
• explain an unfamiliar codebase

It is a good candidate if you are comfortable in a terminal, your data must stay on your machines, and you want the option of a local model, with no API fees.

Access and human control

According to its documentation, SWE-agent can:

• run commands in a terminal
• read and edit files
• call online services and APIs

By default it acts without asking for confirmation. Turn on an approval mode if it has one, or limit its rights to the bare minimum.

SWE-agent pricing

The code is free, under the MIT licence.

Getting started with SWE-agent

1. Install it: the project ships as a Python package (install with pip or uv). The exact command is in the repository README.
2. Pick the model: an API key from a provider, or a local model if your machine has enough graphics memory (the VRAM calculator tells you).
3. Give it a first playground with nothing at stake: a test folder, a secondary account or a throwaway project. Only open your real accounts once you have seen how it behaves.
4. Give it a short, checkable task, review the result and its action log, then raise the difficulty step by step.

Security: risk level

A coding agent runs commands on your machine: work on a Git branch, review the changes and isolate it in a container for long tasks.

Points found for SWE-agent:

• Sensitive access: it can run commands in a terminal, with no established default human approval.
• Outside content: it reads web pages or API responses, which may contain booby-trapped instructions (prompt injection).

Three habits: least privilege (minimal rights, dedicated keys), human approval for irreversible actions, a sandbox for code execution. The AI agent security check reviews your setup in a few minutes.

Project activity and releases

Created on April 2, 2024, the SWE-agent/SWE-agent repository has 20,630 stars, 2,263 forks and 58 open issues, with 2,182 commits in total. Last change 3 months ago.

Over the last 52 weeks: 55 commits, an average of 1.1 per week.

10 releases in total; 0 in the last twelve months. Latest release: v1.1.0, on May 22, 2025.

SWE-agent vs other coding agents

GitHub stars of the best-rated open-source projects in the coding agents family. Stars measure attention, not quality: a heavily promoted project collects them fast, a specialised tool will have few.

SWE-agent and other coding agents at a glance

The 7 best-ranked agents in the same family, 7 of them open source. The score out of 100 only applies to open-source projects; for proprietary services we show the published entry price. A dash marks information the documentation does not state.

How we rated it

Score: 62/100, computed only from public, verifiable data, with no subjective testing or partnership:

• Adoption 28/40: 20,630 stars on a log scale (40 points from about 200,000).
• Activity 9/30: last commit 3 months ago, 0 releases in six months, 55 commits in a year.
• Framework 25/30: licence, default human approval, self-hosting, model choice and documentation site.

The score does not say whether the agent will succeed at your tasks: it measures how solid the project is. The full grid is on the method page.