Open SWE

Open SWE is an open-source framework that provides core architectural components for internal coding agents.

Open SWE is an open-source framework designed to help engineering organizations build internal coding agents. Built on Deep Agents and LangGraph, it provides core architectural components like isolated cloud sandboxes, curated toolsets, and subagent orchestration. Tasks run in dedicated cloud sandboxes with full shell access, using providers like Modal, Daytona, Runloop, and LangSmith. The system integrates directly with workflows in Slack, Linear, and GitHub, allowing agents to ingest rich context, execute commands safely, and open pull requests. It is built for engineering teams looking to deploy custom coding agents into their existing development environments without adopting new interfaces.

Open SWE at a glance

Best for: Software engineer
Runs on: Slack, CLI, API, open source
Pricing: Free
Released: May 2025
Category: AI coding tool
Website: langchain.com

Key features

Isolated cloud execution sandboxes
Curated toolsets for tasks
Slack, Linear, and GitHub integration
Subagent orchestration and delegation
Deterministic middleware for safety nets
Context gathering from AGENTS.md and sources

Use it for

Executing coding tasks in isolated cloud sandboxes
Responding to developer prompts in Slack threads
Reading and processing Linear issues automatically
Addressing GitHub PR review comments and pushing fixes

Companions

Tools that articles about Open SWE recommend using with it, each with its job.

Context7 — Provides up-to-date documentation for AI agents and code editors.
Ollama — Run local models at zero marginal cost, with code kept on your machine.
OpenRouter — Access over 500 models and 80 providers through one unified API.
Daytona — Runs sessions in isolated sandboxes synced to git branches.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps

Alternatives to Open SWE

OpenCode — Works with 75+ model providers, local models, and existing subscriptions
SWE-agent — Research coding agent that scores well on SWE-bench
OpenSandbox — Provides isolated environments with multi-language SDKs and lifecycle management.
OpenHands — Runs autonomous agents locally, in the cloud, or inside your VPC with complete control.
mini-SWE-agent — It offers high performance with a simplified, minimal codebase.
iii — Adds services as workers in any language without writing glue code.
OpenChamber — Run and review multi-model AI coding agents from desktop, browser, and mobile devices.
OpenClaude — Connects one terminal interface to over 200 different AI models.
Open Agents Template — Spawn autonomous coding agents with full sandboxes and durable workflows.
OpenTag — It keeps coding agents connected to local environments while centralizing state in Slack.
Command Code — Repairs open model tool calls and learns developer patterns automatically.
Freebuff — Access multiple coding AI models for free without subscriptions.

All Open SWE alternatives