# Open SWE

LangChain's open-source asynchronous coding agent for internal software engineering workflows.

## Agent Decision Summary
- Risk level: moderate
- Source confidence: high
- Recommended workflows: Coding agent workflow
- Permission surface: shell/files
- Agent JSON: https://www.openagent.bot/agents/open-swe.agent.json

## Summary
Open SWE is an open-source asynchronous coding agent from LangChain. It is designed for internal coding-agent workflows where tasks can run in the background, produce code changes, and fit into software engineering review loops.


## Guide
Open SWE is an open-source asynchronous coding agent from LangChain.

### What it is
It is a software engineering agent for background coding workflows rather than only interactive chat.

### Why it matters
Asynchronous coding agents can fit into issue, branch, review, and CI workflows if teams keep human review in the loop.

### How it works
Start with a low-risk internal repository task, require review before merge, and compare output quality with your existing coding-agent stack.


### FAQ
- Is Open SWE open source?
  - Yes. The GitHub repository is listed under the MIT license.
- Who should evaluate Open SWE?
  - Engineering teams exploring asynchronous coding agents for internal software workflows should evaluate it.
## What It Does
It is a software engineering agent for background coding workflows rather than only interactive chat.

## How To Evaluate
Start with a low-risk internal repository task, require review before merge, and compare output quality with your existing coding-agent stack.

## Why It Matters
Coding agents are shifting from interactive copilots to asynchronous teammates. Open SWE matters because it focuses on background software engineering work rather than only editor-time completion.


## Best For
- Teams evaluating asynchronous coding agents
- Developers comparing open-source alternatives to hosted SWE agents
- Engineering orgs experimenting with internal coding-agent workflows

## Not For
- Users who only need autocomplete inside an IDE
- Teams that cannot review agent-generated code changes before merge

## What It Actually Does
- Asynchronous coding workflow: Open SWE is positioned as an asynchronous coding agent.
  - Why it matters: Background coding agents can take on larger tasks than synchronous chat-only assistants.
- Internal engineering focus: The project homepage frames it around internal coding-agent workflows.
  - Why it matters: Engineering teams need reviewable, auditable workflows rather than one-off generated snippets.
- LangChain ecosystem: Open SWE is maintained under the LangChain GitHub organization.
  - Why it matters: LangChain's agent and orchestration ecosystem gives the project a familiar foundation for many builders.

## Typical Use Cases
- Background coding tasks: Assign scoped engineering tasks for an agent to work on asynchronously.
- Internal agent pilot: Evaluate how an open-source coding agent fits into branch, review, and CI workflows.
- SWE agent comparison: Compare Open SWE with terminal coding agents and hosted SWE automation products.

## How It Compares
- When to choose Open SWE: Compare it with nearby agents by looking at hosting model, integration surface, license, and whether the official docs show the workflow you need.

## Fit Matrix
- Coding agent workflow: strong. Open SWE has multiple signals for coding agent workflow, including matching tags, capabilities, category, or positioning. Required check: Run a small repository change and inspect the diff, tests, and rollback path.
- Browser automation: partial. Open SWE has at least one signal for browser automation, but should be checked against a real task before adoption. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
- Evaluation and observability: partial. Open SWE has at least one signal for evaluation and observability, but should be checked against a real task before adoption. Required check: Add one repeatable test case and confirm results can run again in review or CI.
- Reusable skill workflow: partial. Open SWE has at least one signal for reusable skill workflow, but should be checked against a real task before adoption. Required check: Run one skill end to end and check whether it produces evidence or structured output.
- Connector or protocol layer: weak. Open SWE is not primarily positioned for connector or protocol layer in the current metadata. Required check: Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.
- Local or private AI stack: weak. Open SWE is not primarily positioned for local or private ai stack in the current metadata. Required check: Verify hardware requirements, data path, storage, and whether all calls stay in your environment.

## Evidence
- verified: Open SWE is listed as open source. Source: License metadata: MIT
- verified: Open SWE has a recorded GitHub repository: langchain-ai/open-swe. Source: Resource facts and GitHub source link.
- inferred: Open SWE supports these recorded deployment modes: cloud. Source: OpenAgent decision signal metadata.
- inferred: Open SWE is tagged with workflow orchestration, automation capabilities. Source: OpenAgent capability taxonomy.

## Missing Checks
- Dedicated docs link is missing.
- Repository freshness has not been recorded.

## Next Actions
- Inspect repository: https://github.com/langchain-ai/open-swe
- Open Homepage: https://www.langchain.com/blog/open-swe-an-open-source-framework-for-internal-coding-agents

## Facts
- Category: agents
- Resource type: agent
- Open source: yes
- License: MIT
- Last verified: 2026-06-11
- GitHub repo: langchain-ai/open-swe
- GitHub stars: 9944

## Capabilities
- workflow-orchestration
- automation

## Structured Use Case Tags
- developer-workflow

## Getting Started
- Open the GitHub repository: https://github.com/langchain-ai/open-swe
- Read the launch article: https://www.langchain.com/blog/open-swe-an-open-source-framework-for-internal-coding-agents

## Links
- GitHub: https://github.com/langchain-ai/open-swe
- Homepage: https://www.langchain.com/blog/open-swe-an-open-source-framework-for-internal-coding-agents

## Structured Outputs
- JSON: https://www.openagent.bot/agents/open-swe.json
- Markdown: https://www.openagent.bot/agents/open-swe.md
- Agent JSON: https://www.openagent.bot/agents/open-swe.agent.json
- Canonical: https://www.openagent.bot/agents/open-swe