> ## Documentation Index > Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-naomid-1776417660-b4d4d36.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Deploy with the CLI > Deploy a model-agnostic, open source agent to production with the Deep Agents CLI Deep Agents Deploy takes your agent configuration and deploys it as a [LangSmith Deployment](/langsmith/deployment): a horizontally scalable server with 30+ endpoints including MCP, A2A, Agent Protocol, human-in-the-loop, and memory APIs. Built on open standards: * **Open source harness**: MIT licensed, available for [Python](https://github.com/langchain-ai/deepagents) and [TypeScript](https://github.com/langchain-ai/deepagentsjs) * **[AGENTS.md](https://agents.md/)**: open standard for agent instructions * **[Agent Skills](https://agentskills.io/)**: open standard for agent knowledge and actions * **Any model, any sandbox**: no provider lock-in * **Open protocols**: [MCP](https://modelcontextprotocol.io/docs/getting-started/intro), [A2A](https://a2a-protocol.org/latest/), [Agent Protocol](https://github.com/langchain-ai/agent-protocol) * **Self-hostable**: LangSmith Deployments can be self-hosted so memory stays in your infrastructure Deep Agents Deploy is currently in beta. APIs, configuration format, and behavior may change between releases. See the [releases page](https://github.com/langchain-ai/deepagents/releases) for detailed changelogs. ## Compare to Claude Managed Agents | | Deep Agents Deploy | Claude Managed Agents | | ----------------- | ----------------------------------------------------------------------------------------------------------------------------------- | -------------------------- | | Model support | OpenAI, Anthropic, Google, Bedrock, Azure, Fireworks, Baseten, OpenRouter, [many more](/oss/python/integrations/providers/overview) | Anthropic only | | Harness | Open source (MIT) | Proprietary, closed source | | Sandbox | LangSmith, Daytona, Modal, Runloop, or [custom](/oss/python/contributing/implement-langchain#sandboxes) | Built in | | MCP support | ✅ | ✅ | | Skill support | ✅ | ✅ | | AGENTS.md support | ✅ | ❌ | | Agent endpoints | MCP, A2A, Agent Protocol | Proprietary | | Self hosting | ✅ | ❌ | ## What you're deploying `deepagents deploy` packages your agent configuration and deploys it as a [LangSmith Deployment](/langsmith/deployment). You configure your agent with a few parameters: | Parameter | Description | | --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **`model`** | The LLM to use. Any provider works — see [supported models](/oss/python/deepagents/models#supported-models). | | **`AGENTS.md`** | The system prompt, loaded at the start of each session. | | **`skills`** | [Agent Skills](https://agentskills.io/) for specialized knowledge and actions. Skills are synced into the sandbox so the agent can execute them at runtime. See [skills docs](/oss/python/deepagents/skills). | | **`mcp.json`** | MCP tools (HTTP/SSE). See [MCP docs](/oss/python/langchain/mcp). | | **`sandbox`** | Optional execution environment. See [sandbox providers](#sandbox-providers). | ## Install Install the CLI or run directly with `uvx`: ```bash uv theme={null} uv tool install deepagents-cli ``` ```bash uvx (no install) theme={null} uvx deepagents-cli deploy ``` ## Usage ```bash theme={null} deepagents init [name] [--force] # scaffold a new project deepagents dev [--config deepagents.toml] [--port 2024] [--allow-blocking] # bundle and run locally deepagents deploy [--config deepagents.toml] [--dry-run] # bundle and deploy ``` By default, `deepagents deploy` looks for `deepagents.toml` in the current directory. Pass `--config` to use a different path: ```bash theme={null} deepagents deploy --config path/to/deepagents.toml ``` ### `deepagents init` Scaffold a new agent project: ```bash theme={null} deepagents init my-agent ``` This creates the following files: | File | Purpose | | ----------------- | ------------------------------------------------------------------------------------- | | `deepagents.toml` | Agent config — name, model, optional sandbox | | `AGENTS.md` | System prompt loaded at session start | | `.env` | API key template (`GOOGLE_API_KEY`, `LANGSMITH_API_KEY`, etc.) | | `mcp.json` | MCP server configuration (empty by default) | | `skills/` | Directory for [Agent Skills](https://agentskills.io/), with an example `review` skill | After init, edit `AGENTS.md` with your agent's instructions and run `deepagents deploy`. ## Project layout The deploy command uses a convention-based project layout. Place the following files alongside your `deepagents.toml` and they are automatically discovered: ```txt theme={null} my-agent/ ├── deepagents.toml ├── AGENTS.md ├── .env ├── mcp.json └── skills/ ├── code-review/ │ └── SKILL.md └── data-analysis/ └── SKILL.md ``` | File/directory | Purpose | Required | | -------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | | `AGENTS.md` | [Memory](/oss/python/deepagents/memory) for the agent. Provides persistent context (project conventions, instructions, preferences) that is always loaded at startup. | Yes | | `skills/` | Directory of [skill](/oss/python/deepagents/skills) definitions. Each subdirectory should contain a `SKILL.md` file. | No | | `mcp.json` | [MCP](https://modelcontextprotocol.io/) server configuration. Only `http` and `sse` transports are supported in deployed contexts. | No | | `.env` | Environment variables (API keys, secrets). Placed alongside `deepagents.toml` at the project root. | No | `mcp.json` must only contain servers using `http` or `sse` transports. Servers using `stdio` transport are not supported in deployed environments because there is no local process to spawn. Convert stdio servers to HTTP or SSE before deploying. ## Configuration file `deepagents.toml` configures the agent's identity and sandbox environment. Only the `[agent]` section is required. The `[sandbox]` section is optional and defaults to no sandbox. ### `[agent]` (Required) Core agent identity. For more on model selection and provider configuration, see [supported models](/oss/python/deepagents/models#supported-models). Name for the deployed agent. Used as the assistant identifier in LangSmith. Model identifier in `provider:model` format. See [supported models](/oss/python/deepagents/models#supported-models). ```toml deepagents.toml theme={null} [agent] name = "research-assistant" model = "google_genai:gemini-3.1-pro-preview" ``` The `name` field is the only required value in the entire configuration file. Everything else has defaults. Skills, MCP servers, and model dependencies are auto-detected from the project layout — you don't declare them in `deepagents.toml`: * **Skills**: the bundler recursively scans `skills/`, skipping hidden dotfiles, and bundles the rest. * **MCP servers**: if `mcp.json` exists, it is included in the deployment and [`langchain-mcp-adapters`](https://pypi.org/project/langchain-mcp-adapters/) is added as a dependency. Only HTTP/SSE transports are supported (stdio is rejected at bundle time). * **Model dependencies**: the `provider:` prefix in the `model` field determines the required `langchain-*` package (e.g., `google_genai` -> `langchain-google-genai`). * **Sandbox dependencies**: the `[sandbox].provider` value maps to its partner package (e.g., `daytona` -> `langchain-daytona`). ### `[sandbox]` Configure the isolated execution environment where the agent runs code. Sandboxes provide a container with a filesystem and shell access, so untrusted code cannot affect the host. For supported providers and advanced sandbox configuration, see [sandboxes](/oss/python/deepagents/sandboxes). When omitted or set to `provider = "none"`, the sandbox is disabled. Sandboxes are for if you need code execution or skill script execution. Sandbox provider. Determines where the container runs. Supported values: `"none"`, `"daytona"`, `"modal"`, `"runloop"`, `"langsmith"` (private beta). See [sandbox integrations](/oss/python/integrations/sandboxes) for provider details. Provider-specific template name for the sandbox environment. Base Docker image for the sandbox container. Sandbox lifecycle scope. `"thread"` creates one sandbox per conversation. `"assistant"` shares a single sandbox across all conversations for the same assistant. **Scope behavior:** * `"thread"` (default): Each conversation gets its own sandbox. Different threads get different sandboxes, but the same thread reuses its sandbox across turns. Use this when each conversation should start with a clean environment. * `"assistant"`: All conversations share one sandbox. Files, installed packages, and other state persist across conversations. Use this when the agent maintains a long-lived workspace like a cloned repo. ### `.env` Place a `.env` file alongside `deepagents.toml` with your API keys: ```bash theme={null} # Required — model provider keys ANTHROPIC_API_KEY=sk-... OPENAI_API_KEY=sk-... # ...etc. # Required for deploy and LangSmith sandbox LANGSMITH_API_KEY=lsv2_... # Optional — sandbox provider keys DAYTONA_API_KEY=... MODAL_TOKEN_ID=... MODAL_TOKEN_SECRET=... RUNLOOP_API_KEY=... ``` ## Sandbox providers Set `[sandbox].provider` in `deepagents.toml` and add the required env vars to `.env`. For available providers, see [sandbox integrations](/oss/python/integrations/sandboxes). For lifecycle patterns and SDK usage, see [sandboxes](/oss/python/deepagents/sandboxes). ## Deployment endpoints The deployed server exposes: * [**MCP**](https://modelcontextprotocol.io/docs/getting-started/intro): call your agent as a tool from other agents * [**A2A**](https://a2a-protocol.org/latest/): multi-agent orchestration via A2A protocol * [**Agent Protocol**](https://github.com/langchain-ai/agent-protocol): standard API for building UIs * [**Human-in-the-loop**](/oss/python/deepagents/human-in-the-loop): approval gates for sensitive actions * [**Memory**](/oss/python/deepagents/memory): short-term and long-term memory access ## Examples A content writing agent that only needs a model and system prompt, with no code execution: ```toml deepagents.toml theme={null} [agent] name = "deepagents-deploy-content-writer" model = "google_genai:gemini-3.1-pro-preview" ``` A coding agent with a LangSmith sandbox for running code: ```toml deepagents.toml theme={null} [agent] name = "deepagents-deploy-coding-agent" model = "google_genai:gemini-3.1-pro-preview" [sandbox] provider = "langsmith" template = "coding-agent" image = "python:3.12" ``` ***
[Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/deepagents/deploy.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose). [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.