open-swe 是 AI Skill Hub 本期精选Agent工作流之一。已获得 9.8k 颗 GitHub Star,综合评分 9.1 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
open-swe 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
open-swe 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install open-swe
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install open-swe
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/langchain-ai/open-swe
cd open-swe
pip install -e .
# 验证安装
python -c "import open_swe; print('安装成功')"
# 命令行使用
open-swe --help
# 基本用法
open-swe input_file -o output_file
# Python 代码中调用
import open_swe
# 示例
result = open_swe.process("input")
print(result)
# open-swe 配置文件示例(config.yml) app: name: "open-swe" debug: false log_level: "INFO" # 运行时指定配置文件 open-swe --config config.yml # 或通过环境变量配置 export OPEN_SWE_API_KEY="your-key" export OPEN_SWE_OUTPUT_DIR="./output"
<br>
Elite engineering orgs like Stripe, Ramp, and Coinbase are building their own internal coding agents — Slackbots, CLIs, and web apps that meet engineers where they already work. These agents are connected to internal systems with the right context, permissioning, and safety boundaries to operate with minimal human oversight.
Open SWE is the open-source version of this pattern. Built on LangGraph and Deep Agents, it gives you the same architecture those companies built internally: cloud sandboxes, Slack and Linear invocation, subagent orchestration, and automatic PR creation — ready to customize for your own codebase and workflows.
[!NOTE] 💬 Read the announcement blog post here
---
@openswe in a comment to kick off a task---
Every task runs in its own isolated cloud sandbox — a remote Linux environment with full shell access. The repo is cloned in, the agent gets full permissions, and the blast radius of any mistake is fully contained. No production access, no confirmation prompts.
Open SWE supports multiple sandbox providers out of the box — Modal, Daytona, Runloop, and LangSmith — and you can plug in your own. See the Customization Guide for details.
This follows the principle all three companies converge on: isolate first, then give full permissions inside the boundary.
| Decision | Open SWE | Stripe (Minions) | Ramp (Inspect) | Coinbase (Cloudbot) |
|---|---|---|---|---|
| **Harness** | Composed (Deep Agents/LangGraph) | Forked (Goose) | Composed (OpenCode) | Built from scratch |
| **Sandbox** | Pluggable (Modal, Daytona, Runloop, etc.) | AWS EC2 devboxes (pre-warmed) | Modal containers (pre-warmed) | In-house |
| **Tools** | ~15, curated | ~500, curated per-agent | OpenCode SDK + extensions | MCPs + custom Skills |
| **Context** | AGENTS.md + issue/thread | Rule files + pre-hydration | OpenCode built-in | Linear-first + MCPs |
| **Orchestration** | Subagents + middleware | Blueprints (deterministic + agentic) | Sessions + child sessions | Three modes |
| **Invocation** | Slack, Linear, GitHub | Slack + embedded buttons | Slack + web + Chrome extension | Slack-native |
| **Validation** | Prompt-driven | 3-layer (local + CI + 1 retry) | Visual DOM verification | Agent councils + auto-merge |
---
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
经综合评估,open-swe 在Agent工作流赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | open-swe |
| Topics | workflowagentagentsaianthropicclaudecodepython |
| GitHub | https://github.com/langchain-ai/open-swe |
| License | MIT |
| 语言 | Python |
收录时间:2026-05-22 · 更新时间:2026-05-22 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端