Ross ROSS = Recommend OSS · open-source software intelligence for agents

langchain-ai/open-swe

An Open-Source Asynchronous Coding Agent observed · 2026-08-28

github.com/langchain-ai/open-swe · homepage · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

63/100

  • Activity 99
  • Release rhythm 35
  • Longevity 33

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 469
  • days_rel: n/a
  • days_push: 7
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

10620 stars · 1243 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Open SWE is an open-source framework from LangChain for building an organization's internal asynchronous coding agent, built on LangGraph and Deep Agents. It provides cloud sandboxes, Slack and Linear invocation, subagent orchestration, and automatic PR creation, ready to customize for your own codebase and workflows.

Use cases

  • build an internal coding agent for my engineering org
  • run an AI agent that fixes GitHub issues and opens pull requests
  • invoke a coding agent from Slack or Linear
  • run coding tasks in isolated cloud sandboxes
  • orchestrate subagents for long-horizon coding tasks
  • self-host an open-source alternative to Claude Code
  • customize an agent harness for my codebase and workflows

When to choose

  • You want to build a customizable internal coding agent following the patterns of Stripe's Minions, Ramp's Inspect, or Coinbase's Cloudbot
  • You need Slack/Linear/GitHub integrations, cloud sandboxes, and automatic PR creation out of the box
  • You want an upgrade path by composing on the Deep Agents framework rather than forking an agent
  • You need asynchronous, long-running agent tasks with minimal human oversight

When to avoid

  • You just want a ready-to-use terminal coding assistant with no customization needs
  • You need a simple synchronous code-completion tool rather than an autonomous agent framework
  • You cannot run cloud sandboxes or don't want agent infrastructure to maintain
  • You need a lightweight agent without LangGraph/Deep Agents dependencies

Facets

framework · maturity active

agent-framework llm-inference workflow-automation developer-tools cli large-language-models developer-tools version-control python cloud self-hosted cross-platform coding-agent langgraph deep-agents slack-integration linear-integration github-prs cloud-sandboxes subagent-orchestration internal-coding-agent ai-agents automation docker

7 sources

Member repositories

RepositoryRoleHealth v2
langchain-ai/open-swemain63

For agents

markdown · JSON · MCP: product_card(name="langchain-ai/open-swe")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem