OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Coding Agents

Swe Agent

Swe Agent is a Python-based autonomous coding agent that takes a GitHub issue, uses a selected language model and tools, and attempts to modify the affected repository to fix the issue. It is an open-source MIT-licensed project available for command-line, server, and self-hosted use, with documented applications in software engineering, coding challenges, and offensive cybersecurity challenge environments.

Independent OpenViST project profile, based on linked sources.

Swe Agent — OpenViST project profile in Coding Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Swe Agent when the task begins with a GitHub issue or another documented coding challenge and you want a configurable agent to inspect and modify repository code. Its documented command-line, batch-mode, and self-hosted orientation suits users who can provide the model and execution environment.

Who it is for

  • Developers handling software issues in GitHub repositories
  • Researchers evaluating language models on software-engineering tasks
  • Builders needing a configurable and hackable coding-agent framework
  • Users working on competitive coding or authorized offensive cybersecurity challenges

Documented uses

  • Turn a GitHub issue description into an attempted repository fix
  • Give a language model tools for code-focused repository work
  • Run configurable software-engineering evaluations such as SWE-bench
  • Support custom coding and challenge-oriented tasks
Before you choose

Requirements & limits

The repository is public, open source, and MIT licensed. The project documentation describes source installation, command-line usage, batch mode, and GitHub Codespaces entry points.

  • GitHub repository issues are the core documented input for the software-fixing workflow.
  • A language model must be selected; the project supports a model of the user's choice rather than requiring one fixed model.
  • Behavior is configured through a YAML file, which supports research and customization.
  • The project is Python-based and oriented toward CLI, server, and self-hosted environments.
  • The README identifies mini-SWE-agent as the simpler successor and recommends it for future use.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Swe AgentTurn a GitHub issue description into an attempted repository fixCLI, Self-hosted, ServerThe repository is public, open source, and MIT licensed. The project documentation describes source installation, command-line usage, batch mode, and GitHub Codespaces entry points.
LlmcodeInspect a project's directory structure with `/tree`.CLIThe documented setup requires an API key and supports an API base URL and model setting. The project is open source under Apache-2.0.
Klaat CodeOpen a project directory for terminal-based coding assistance.CLI, ServerThe README provides a global npm installation command and documents browser sign-in with a KlaatAI account. It also identifies the repository as open source under Apache 2.0.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
2 October 2026
Original website title
SWE-agent/SWE-agent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction