Skip to main content
hc
Submit
toolsSource-backedReview first Safety ✓ Privacy ✓

Open SWE

Open-source framework for building internal coding agents that accept tasks via Slack, Linear, or GitHub, execute code changes in isolated cloud sandboxes, and open draft pull requests automatically.

by LangChain·added 2026-06-05·
CLI
HarnessCLI
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • Each task runs in an isolated cloud Linux sandbox (Modal, Daytona, Runloop, or LangSmith) to prevent production impact.
  • The agent executes shell commands, file operations, web fetches, and HTTP requests inside the sandbox without confirmation prompts — review sandbox provider permissions before deployment.
  • GitHub operations are performed through a GH_TOKEN proxy; scope token permissions to the minimum required repositories.
  • Subagent orchestration can spawn parallel child agents — set appropriate step limits and monitor LangSmith traces to prevent runaway execution.
  • AGENTS.md or CLAUDE.md at the repository root is injected into the system prompt; review this file to control agent behavior and conventions.

Privacy notes

  • Repository code, Linear issue history, and Slack thread history are sent to the configured model provider API.
  • Sandbox providers (Modal, Daytona, Runloop, LangSmith) process task execution data according to their own privacy policies.
  • LangSmith tracing, when enabled, logs full agent traces including tool inputs and outputs — configure retention and access controls in your LangSmith organization.
  • GitHub OAuth tokens and model API keys should be stored as secrets and never committed to the repository.

Prerequisites

  • GitHub account with OAuth access for repository operations.
  • A model API key (Anthropic, OpenAI, or compatible provider).
  • A LangSmith API key when using LangSmith as the sandbox provider.
  • Slack workspace, Linear workspace, or GitHub repository access for the desired trigger integrations.
  • Python 3.10+ and Node.js for local development.

Schema details

Install type
copy
Troubleshooting
No
Source repository stats
Scope
Source repo
Tool listing metadata
Pricing
open-source
Disclosure
editorial
Application category
DeveloperApplication
Operating system
macOS, Windows, Linux
Full copyable content
## Overview

Open SWE is a practical reference implementation for teams that want to run
coding agents against their own repositories without building the orchestration
layer from scratch. It mirrors patterns used by engineering teams at Stripe,
Ramp, and Coinbase for internal coding agents.

The framework composes on LangGraph and the Deep Agents harness. Each task
runs in a dedicated cloud sandbox (Modal, Daytona, Runloop, or LangSmith),
executes the agent loop with roughly fifteen curated tools, and opens a draft
PR on completion. Parallel tasks get separate sandboxes with no queuing.

## Features

- Multi-platform invocation through Slack mentions, Linear comments with
  `@openswe`, and GitHub PR comment replies.
- Isolated, reusable cloud sandboxes per task thread with pluggable providers
  (Modal, Daytona, Runloop, LangSmith).
- Automatic draft pull request creation and linking back to the source task.
- Subagent orchestration for parallel subtasks via the `task` tool.
- Configurable model support and a curated tool set covering shell execution,
  file operations, web fetches, and API requests.
- A web dashboard for authentication, team settings, and direct agent chat.

## Use Cases

- Triage and resolve routine engineering tasks raised in Linear or Slack.
- Stand up an internal coding agent that respects organization conventions via
  an `AGENTS.md` or `CLAUDE.md` context file.
- Run multiple coding tasks in parallel without manual environment setup.
- Prototype a customizable, self-hosted alternative to closed coding agents.

## Disclosure

Editorial listing. No paid placement or affiliate relationship.

About this resource

Overview

Open SWE is a practical reference implementation for teams that want to run coding agents against their own repositories without building the orchestration layer from scratch. It mirrors patterns used by engineering teams at Stripe, Ramp, and Coinbase for internal coding agents.

The framework composes on LangGraph and the Deep Agents harness. Each task runs in a dedicated cloud sandbox (Modal, Daytona, Runloop, or LangSmith), executes the agent loop with roughly fifteen curated tools, and opens a draft PR on completion. Parallel tasks get separate sandboxes with no queuing.

Features

  • Multi-platform invocation through Slack mentions, Linear comments with @openswe, and GitHub PR comment replies.
  • Isolated, reusable cloud sandboxes per task thread with pluggable providers (Modal, Daytona, Runloop, LangSmith).
  • Automatic draft pull request creation and linking back to the source task.
  • Subagent orchestration for parallel subtasks via the task tool.
  • Configurable model support and a curated tool set covering shell execution, file operations, web fetches, and API requests.
  • A web dashboard for authentication, team settings, and direct agent chat.

Use Cases

  • Triage and resolve routine engineering tasks raised in Linear or Slack.
  • Stand up an internal coding agent that respects organization conventions via an AGENTS.md or CLAUDE.md context file.
  • Run multiple coding tasks in parallel without manual environment setup.
  • Prototype a customizable, self-hosted alternative to closed coding agents.

Disclosure

Editorial listing. No paid placement or affiliate relationship.

#coding-agent#automation#langgraph#sandboxed-execution#open-source#github-automation#slack-integration#linear-integration

Source citations

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.