langchain-ai/open-swe

An Open-Source Asynchronous Coding Agent

What it solves

Open SWE provides a repeatable, automated system for software engineering tasks. It addresses the end-to-end lifecycle of code changes by investigating issues, implementing solutions in isolated environments, validating code, and managing pull requests. It also assists with code reviews, monitors CI pipelines, and learns from repository-specific feedback.

How it works

The project is built on LangGraph for durable execution and Deep Agents for planning and tool-use primitives. It operates by running tasks in persistent, per-thread Linux sandboxes. It integrates with GitHub, Slack, and Linear, allowing users to trigger engineering workflows via issues, PR conversations, or chat. The system supports parallel subagents for research and task execution, and it can be customized with specific models, instructions, and sandbox providers.

Who it’s for

This project is intended for developers and organizations looking to deploy their own autonomous coding agents to handle routine engineering tasks, automate PR reviews, and manage repository maintenance within their own infrastructure.

Highlights

  • Automated Engineering Lifecycle: Handles investigation, implementation, validation, and PR delivery.
  • Durable Execution: Powered by LangGraph to maintain state and handle complex, multi-step agentic workflows.
  • Flexible Integration: Supports triggers from GitHub, Slack, and Linear, with configurable sandbox environments.
  • Review & Monitoring: Includes features for automatic PR reviews, CI monitoring, and responding to feedback.
  • Customizable Architecture: Allows users to define custom skills, tools, and models to fit specific repository needs.

Related

  • Project
    Agent-Field/SWE-AF

    An autonomous software engineering factory that orchestrates a full team of AI agents (PMs, architects, coders, QA) to scope, build, and ship complex code changes across one or more repositories.

  • Project
    datacurve-ai/deep-swe

    DeepSWE is a benchmark for measuring coding agents on 113 long-horizon software engineering tasks from real-world open-source repositories.

  • Project
    superplanehq/superplane

    SuperPlane is an open‑source platform that orchestrates AI coding agents, source‑control, CI and other dev‑ops tools into a visible, repeatable “factory” workflow, turning backlog issues into ready‑to‑review pull requests while preserving execution history and cost data.

  • Project
    jingsewu/open-wes

    An open-source Warehouse Execution System (WES) that provides real-time orchestration and AI-powered optimization for automated warehouses using robots and IoT.

  • Project
    SWE-agent/SWE-agent

    An autonomous AI agent that enables LLMs to fix GitHub issues, find security vulnerabilities, and perform custom coding tasks.