项目处于活跃开发中,会有破坏性变更且暂不接受 issue 和外部贡献;按原样部署需要 Managed Deep Agents 来运行代理,否则需 fork 改造适配自己的运行时;沙箱通常拿到 GitHub App 安装级权限且可能有网络访问,需用最小权限凭据并收紧仓库与集成范围。
open-swe
langchain-aiMIT活跃维护开源异步编码智能体,可后台自动完成改代码、修 bug 等开发任务,支持 Anthropic、OpenAI 等模型。
An Open-Source Asynchronous Coding Agent
pip install -e .README 未说明本地硬件或显存要求;默认在 LangSmith 提供的云端 Linux 沙箱中运行,也可配置其他沙箱提供方或本地执行,本地执行不具备云沙箱隔离。
LangChain 开源的异步编码代理,把调研、改码、验证、提 PR 串成可重复流程
开源异步编码智能体,可后台自动完成改代码、修 bug 等开发任务,支持 Anthropic、OpenAI 等模型。
核心能力
- 在隔离沙箱中调研仓库、改代码并跑针对性验证
- 用子代理并行做调研和独立任务
- 自动审查 PR 并把发现发布到 GitHub,从历史反馈学习
- 用 /baby-sit 监控 PR、诊断 CI 失败并只重跑有证据的 flaky 任务
- 支持从仪表盘、GitHub issue/PR、Slack、Linear 发起会话
容易踩的坑
- desktop-ui-f84450508630cbd79099de49b3d00dcdf3be9a49Desktop UI f84450508630cbd79099de49b3d00dcdf3be9a49pre-release2026-11-09 · 2026-11-09 17:33 UTC
查看更新说明
Standalone desktop UI for backend commit f84450508630cbd79099de49b3d00dcdf3be9a49.
- desktop-v0.3.16-nightly.20261109153507Robin Desktop Nightly 20261109153507pre-release最新正式版2026-11-09 · 2026-11-09 15:42 UTC
- desktop-ui-ed7830da713cd8046d991cb63328166d5ed85a00Desktop UI ed7830da713cd8046d991cb63328166d5ed85a00pre-release2026-11-09 · 2026-11-09 15:28 UTC
查看更新说明
Standalone desktop UI for backend commit ed7830da713cd8046d991cb63328166d5ed85a00.
- desktop-v0.3.16-nightly.20261109140654Robin Desktop Nightly 20261109140654pre-release2026-11-09 · 2026-11-09 14:14 UTC
- desktop-v0.3.16-nightly.20261109082235Robin Desktop Nightly 20261109082235pre-release2026-11-09 · 2026-11-09 08:30 UTC
用户点评
登录用户的真实使用记录,可按版本和硬件筛选还没有人点评。第一个说出真实体验的人最有价值。
Robin
Robin turns engineering work into a repeatable system: investigate a codebase, implement changes, validate them, and deliver a pull request. It also reviews pull requests, learns repository-specific review preferences, monitors CI, and responds to feedback. Built by LangChain, it is open source and deployable in your infrastructure.
[!NOTE] Under active development. Expect breaking changes and rough edges. We’re not accepting issues or external contributions at this time. You’re welcome to explore and fork the code, but correctness, stability, and compatibility are not guaranteed.
If you really want to deploy it yourself, follow the installation guide. Deploying it as is requires Managed Deep Agents, which runs its agent; without it, we recommend forking and adapting the code to your own runtime.
What Robin does
flowchart LR
A[Issues, conversations, PRs, schedules] --> B[Plan and investigate]
B --> C[Implement in an isolated sandbox]
C --> D[Validate and deliver a PR]
D --> E[Review, CI, and feedback]
E -->|Follow-up work| B
- Build: Investigate repositories, edit code, run focused validation, and open or update pull requests.
- Parallelize: Use subagents for research and independent work.
- Review: Run on-demand or opt-in automatic reviews, publish findings to GitHub, and learn from historical feedback.
- Investigate: Use read-only PR chat to understand a change without implementing changes.
- Operate: Schedule recurring tasks and monitor opted-in PRs with
/baby-sit, diagnosing failures and rerunning only evidence-backed flaky jobs. - Customize: Choose models, reasoning effort, instructions, skills, integrations, and sandbox providers.
Start and continue work from the dashboard, GitHub issues and PR conversations, or Slack. In Linear, mention or delegate an issue to the Robin app to open an agent session. Cloud coding follow-ups reuse the thread’s context and sandbox; independent threads can run in parallel.
How it works
Deep Agents supplies planning, filesystem, shell, skills, and subagent primitives.
LangGraph provides durable execution and thread state.
Robin adds engineering tools, integrations, authorization, and user interfaces.
The graph entrypoints are declared in langgraph.json, with an architecture inventory.
Cloud coding runs in persistent, per-thread Linux sandboxes with tooling supplied by workspace scripts or snapshots. An unreachable coding sandbox is not silently replaced. LangSmith is the default sandbox and tracing provider; other providers and local execution are configurable. PR chat does not need a sandbox.
Control and safety
- GitHub access: Coding sandboxes normally receive installation-wide GitHub App access; selected workflows use narrower repository scopes. Workspace repository bindings control routing and preloaded checkouts, not a separate credential boundary. See GitHub access.
- Integrations: MCP connections layer instance-wide, workspace-specific, and personal tools. Configure their scope and credentials in the customization guide.
- Approvals: Workflow-file approval prompts guard detected Git pushes, not every possible shell or API write. Reviewers are instructed not to commit or push; PR chat excludes mutation tools.
Sandboxes have powerful tools and may have network access. Use least-privilege credentials, restrict repositories and integrations, and tailor approval policies to your deployment. Local execution does not provide cloud sandbox isolation.
Documentation
- Robin rollout checklist — External integration updates, desktop upgrade checks, and compatibility boundaries
- Customization guide — Models, sandboxes, tools, skills, prompts, triggers, and middleware
- Plugin guide — Build web apps: sandboxed single-file plugins people add to their sidebar
- Workspaces reference — Routing, settings, images, and access
- Human review in Slack — Review requests in a repository's Slack channel, merged once reviewers approve
- Expedited Slack review — Human approval for small pull requests
- Backend API documentation — Live API docs and the generated OpenAPI schema
- Original announcement — Background on the internal coding-agent framework
- Security policy — Report security concerns privately
License
Robin is licensed under the MIT License.
That license covers Robin's own code only.
It does not cover anything under vendor/, which is not licensed by this repository at all.