Run This Ai
EN DE

Open SWE

Open-source asynchronous coding agent from LangChain — submit coding jobs from Slack, Linear, or GitHub and get pull requests back.

★ 10,498 GitHub MIT coding-agentlangchainlanggraphdeep-agentsslacklinear AI Agents

Overview

Open SWE is an open-source, asynchronous coding agent framework from LangChain, built for engineering organizations that want their own internal coding agent — the same architecture used by elite teams at Stripe, Ramp, and Coinbase. Built on LangGraph and Deep Agents, it lets you submit coding jobs that run in isolated cloud sandboxes with full shell access, then automatically opens pull requests with the results. It ships with a web UI, a Slackbot, and a CLI, integrates with Linear for issue tracking and Slack for team notifications, and supports Modal, Daytona, Runloop, E2B, and LangSmith as sandbox providers. Every task runs in its own isolated environment with a curated toolset, so the blast radius stays small while the agent operates with minimal human oversight. MIT-licensed and already one of the most popular open-source coding agent frameworks.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8192 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  open-swe:
    image: zsssh/open-swe:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/open-swe:/data

Best VPS for Open SWE →

Related tools

Guides & articles