> ## Documentation Index > Fetch the complete documentation index at: https://docs.langchain.com/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 and requires `deepagents-cli>=0.0.36`. 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). | | **`user/`** | Per-user writable memory. If a `AGENTS.md` template is present in the `user` folder, the agents seeds the template per user (if the folder is empty the agents creates an empty `AGENTS.md`). Writable at runtime. Preloaded into the agent's context via the memory middleware. | | **`mcp.json`** | MCP tools (HTTP/SSE). See [MCP docs](/oss/python/langchain/mcp). | | **`subagents/`** | Specialized [subagents](/oss/python/deepagents/subagents) the main agent can delegate to. Each subdirectory contains its own `deepagents.toml`, `AGENTS.md`, and optionally a `skills` folder. See [subagents](#subagents). | | **`sandbox`** | Optional execution environment. Thread-scoped sandboxes are provisioned per thread and will be re-created if the server restarts. Use `scope = "assistant"` if you need sandbox state that persists across threads. See [sandbox providers](#sandbox-providers). | | **`frontend`** | Optional prebuilt React chat UI shipped alongside the agent on the same deployment. Configurable for per-user auth or anonymous mode, with real-time todos, files, and subagent activity panels. See [`[frontend]`](#frontend). | ## Install Install the CLI or run directly with `uvx`: ```bash uv theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} uv tool install deepagents-cli ``` ```bash uvx (no install) theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} uvx deepagents-cli deploy ``` ## Usage ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} 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={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} deepagents deploy --config path/to/deepagents.toml ``` `deepagents deploy` fully rebuils and creates a new revision on every invocation. Use `deepagents dev` for local iteration. ### `deepagents init` Scaffold a new agent project: ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} 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`. Optionally add a `user/` directory with per-user memory templates — see [User Memory](#user-memory). ## 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={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} my-agent/ ├── deepagents.toml ├── AGENTS.md ├── .env ├── mcp.json ├── skills/ │ ├── code-review/ │ │ └── SKILL.md │ └── data-analysis/ │ └── SKILL.md ├── subagents/ │ └── researcher/ │ ├── deepagents.toml │ └── AGENTS.md └── user/ └── AGENTS.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. Read-only at runtime. | Yes | | `skills/` | Directory of [skill](/oss/python/deepagents/skills) definitions. Each subdirectory should contain a `SKILL.md` file. Read-only at runtime. | No | | `user/` | Per-user writable memory. If a `AGENTS.md` template is present in the `user` folder, the agents seeds the template per user (if the folder is empty the agents creates an empty `AGENTS.md`). Writable at runtime. Preloaded into the agent's context via the memory middleware. | No | | `subagents/` | [Subagents](#subagents) the main agent can delegate to. Each subdirectory must contain a `deepagents.toml`, `AGENTS.md`, and optionally a `skills` folder. Auto-discovered at bundle time. | 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={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} [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, user memories, subagents, MCP servers, and model dependencies are auto-detected from the project layout: * **Skills**: the bundler recursively scans `skills/`, skipping hidden dotfiles, and bundles the rest. * **User memory**: if `user/` exists, a single `AGENTS.md` is bundled as per-user memory (from `user/AGENTS.md` if present, otherwise empty). At runtime, each user gets their own copy (seeded on first access, never overwritten). The agent can read from and write to this file. * **Subagents**: if `subagents/` exists, the bundler scans for valid subdirectories (each must contain `deepagents.toml` and `AGENTS.md`). The main agent receives a `task` tool to delegate work to each subagent by name. See [subagents](#subagents). * **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`). This includes models specified in subagent configs. * **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. ### `[auth]` Add an `[auth]` section to control authentication on the deployed agent. When present, the bundler generates an `auth.py` file wired into the deployment automatically. `[auth]` is **required** when `[frontend].enabled = true`; otherwise it is optional (without it, LangSmith Deployment's default `x-api-key` requirement applies). Auth provider. Supported values: `"supabase"`, `"clerk"`, `"anonymous"`. ```toml deepagents.toml theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} [agent] name = "my-agent" model = "google-genai:gemini-3.1-pro-preview" [auth] provider = "supabase" # supabase | clerk | anonymous ``` The required environment variables depend on the provider: | Provider | Required env vars | | ----------- | -------------------------------------------------- | | `supabase` | `SUPABASE_URL`, `SUPABASE_PUBLISHABLE_DEFAULT_KEY` | | `clerk` | `CLERK_SECRET_KEY` | | `anonymous` | None | Add these to your `.env` alongside your other credentials. The bundler validates that all required vars are present at deploy time and fails fast with a clear error if any are missing. **Runtime behavior:** * Unauthenticated requests return `401`. * On success, the authenticated user's identity is injected into `config.configurable.langgraph_auth_user_id`. * All resources (threads, runs, store) are automatically scoped per user via `metadata.owner`. * LangSmith Studio bypasses auth for local development. ### `[frontend]` Frontend deployment requires `deepagents-cli>=0.0.43`. Optionally enable `[frontend]` to ship a prebuilt React chat UI alongside your agent on the same deployment. The frontend is mounted at `/app` on your deployment URL; your LangGraph API stays at the root (`/threads`, `/runs`, `/assistants`). Every frontend uses one of three authentication providers — Clerk, Supabase, or anonymous (see [`[auth]`](#auth) below). If `true`, bundle the default chat UI into the deployment. Display name shown in the UI header and browser tab. Subtitle shown under the app name in the header and on the empty-state hero. Use it to describe what the agent does. Suggestion chips shown on the empty-state when there are no messages. Defaults to a generic research-themed set; override to tailor the chips to your agent. ```toml deepagents.toml theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} [agent] name = "my-agent" model = "anthropic:claude-sonnet-4-6" [auth] provider = "supabase" # or "clerk" [frontend] enabled = true app_name = "My Agent" subtitle = "Your AI research assistant" prompts = [ "Summarize this paper", "Find related work", "Draft an outline", ] ``` **Authentication providers:** `[auth]` is required when `[frontend].enabled = true`. Pick one of three providers: * **Clerk** (`[auth] provider = "clerk"`) — per-user real authentication. Each user signs in; threads and memory are scoped per user. * **Supabase** (`[auth] provider = "supabase"`) — per-user real authentication. Same per-user scoping as Clerk. * **Anonymous** (`[auth] provider = "anonymous"`) — the bundler ships a permissive auth handler that overrides LangSmith Deployment's default `x-api-key` requirement so the frontend can reach `/threads`, which means anyone with the deploy URL can call the API. The frontend assigns each browser a UUID cookie and filters the thread picker by it (UX-only scoping, not security). The CLI requires an interactive `y/N` confirmation before pushing. **What you get:** * Streaming chat with the agent * Thread picker with auto-generated titles from the first user message * Real-time todos, files, and subagent activity panels that reflect your deep agent's live graph state * Light/dark theme toggle that follows OS preference on first load and persists after * (Clerk / Supabase only) Sign-in / sign-up / sign-out flows — Clerk ships its full widget (social logins, password reset); Supabase ships email/password with a built-in password reset flow **Environment variables:** The frontend reuses most of what `[auth]` already requires. Only Clerk needs one additional browser-facing key. | Provider | Additional var | | ---------- | ------------------------------------------------------------------------------------------ | | `supabase` | None — reuses `SUPABASE_URL` and `SUPABASE_PUBLISHABLE_DEFAULT_KEY` from `[auth]` | | `clerk` | `CLERK_PUBLISHABLE_KEY` (browser-facing publishable key; distinct from `CLERK_SECRET_KEY`) | **Post-deploy setup:** After deploying, add your deployment URL to your auth provider's dashboard so auth redirects land back in the app. This is a one-time step per deployment URL. * **Clerk:** Dashboard → your application → **Domains** → add your deployment host (e.g. `clerk-abc.us.langgraph.app`). Clerk development instances auto-whitelist localhost; production deployment URLs need explicit whitelisting. * **Supabase:** Dashboard → **Authentication** → **URL Configuration** → add `https:///app/**` to **Redirect URLs**. Without this, password-reset and email-confirmation links won't route back to your app. ### `.env` Place a `.env` file alongside `deepagents.toml` with your API keys: ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} # 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=... # Required if [auth] provider = "supabase" SUPABASE_URL=https://your-project.supabase.co SUPABASE_PUBLISHABLE_DEFAULT_KEY=eyJhbGc... # Required if [auth] provider = "clerk" CLERK_SECRET_KEY=sk_test_... # Required if [frontend].enabled = true AND [auth] provider = "clerk" CLERK_PUBLISHABLE_KEY=pk_test_... ``` ## Authentication The runtime auth posture depends on `[auth]`: * **`[auth] provider = "supabase"` or `"clerk"`** — per-user real authentication. Pass the user's auth-provider token in the `Authorization` header. * **`[auth] provider = "anonymous"`** — the bundler ships a permissive auth handler. The API is open to anyone with the deploy URL. No header required. (Required when shipping `[frontend]` without real per-user auth.) * **No `[auth]` section** — the deploy falls back to LangSmith Deployment's default `x-api-key` requirement. Pass your LangSmith API key in the `x-api-key` header. Only valid when `[frontend].enabled` is `false` or unset. When `[auth]` is configured for `supabase` or `clerk`, pass the token from your auth provider in the `Authorization` header: ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} curl -X POST https://your-deployment-url/threads \ -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \ -H "Content-Type: application/json" \ -d '{"metadata": {}}' ``` ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} from langgraph_sdk import get_client client = get_client( url="https://your-deployment-url", headers={"Authorization": "Bearer YOUR_ACCESS_TOKEN"}, ) thread = await client.threads.create() ``` | Provider | Where to get the token | | -------- | ----------------------------------------------------------------- | | Supabase | Supabase session `access_token` from `supabase.auth.getSession()` | | Clerk | Clerk session token from `getToken()` | Each user's threads and memory are isolated automatically—User B cannot see User A's threads. ## 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 with per-user preferences that the agent can update: ```toml deepagents.toml theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} [agent] name = "deepagents-deploy-content-writer" model = "google_genai:gemini-3.1-pro-preview" ``` ```txt theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} my-content-writer/ ├── deepagents.toml ├── AGENTS.md ├── skills/ │ ├── blog-post/SKILL.md │ └── social-media/SKILL.md └── user/ └── AGENTS.md # writable — agent learns user preferences ``` A coding agent with a LangSmith sandbox for running code: ```toml deepagents.toml theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} [agent] name = "deepagents-deploy-coding-agent" model = "google_genai:gemini-3.1-pro-preview" [sandbox] provider = "langsmith" template = "coding-agent" image = "python:3.12" ``` A GTM strategy agent that delegates research to a subagent: ```txt theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} my-gtm-agent/ ├── deepagents.toml ├── AGENTS.md ├── skills/ │ └── competitor-analysis/ │ └── SKILL.md └── subagents/ └── market-researcher/ ├── deepagents.toml ├── AGENTS.md └── skills/ └── analyze-market/ └── SKILL.md ``` A lightweight internal-demo agent with the bundled UI in anonymous mode (no signup, no infrastructure): ```toml deepagents.toml theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} [agent] name = "internal-demo" model = "anthropic:claude-sonnet-4-6" [auth] provider = "anonymous" # API open to anyone with the URL — confirm at deploy time [frontend] enabled = true ``` ## User Memory User memory gives each user their own writable `AGENTS.md` that persists across conversations. To enable it, create a `user/` directory at your project root: ```txt theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} user/ └── AGENTS.md # optional — seeded as empty if not provided ``` If the `user/` directory exists (even if empty), every user gets their own `AGENTS.md` at `/memories/user/AGENTS.md`. If you provide `user/AGENTS.md`, its contents are used as the initial template; otherwise an empty file is seeded. At runtime, user memory is scoped per user via custom auth (`runtime.server_info.user.identity`). The first time a user interacts with the agent, their namespace is seeded with the template. Subsequent interactions reuse the existing file — the agent's edits persist, and redeployments never overwrite user data. ### How it works 1. **Bundle time** — the bundler reads `user/AGENTS.md` (or uses an empty string) and includes it in the seed payload. 2. **Runtime (first access)** — when the agent sees a `user_id` for the first time, it writes the `AGENTS.md` template to the store under that user's namespace. Existing entries are never overwritten. 3. **Preloaded** — the user `AGENTS.md` is passed to the memory middleware, so the agent sees its contents in context at the start of every conversation. 4. **Writable** — the agent can update it using the `edit_file` tool. The shared `AGENTS.md` file and skills folder are read-only. ### Permissions | Path | Writable | Scope | | ------------------------------- | ---------------- | --------------------------- | | `/memories/AGENTS.md` | No | Shared (assistant-scoped) | | `/memories/skills/**` | No | Shared (assistant-scoped) | | `/memories/user/**` | Yes | Per-user (`user_id`-scoped) | | `/memories/subagents//**` | By subagent only | Per-subagent (isolated) | ### User identity The `user_id` is resolved from custom auth via `runtime.user.identity`. The platform injects the authenticated user's identity automatically — no need to pass it through `configurable`. If no authenticated user is present, user memory features are gracefully skipped for that invocation. ## Subagents Subagents let the main agent delegate specialized tasks to isolated child agents. Each subagent has its own system prompt, optional skills, and optional MCP tools. The main agent receives a `task` tool that dispatches work to subagents by name. For background on why subagents are useful and how they work at the SDK level, see [Subagents](/oss/python/deepagents/subagents). ### Directory structure Create a `subagents/` directory at your project root. Each subdirectory is a subagent: ```txt theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} my-agent/ ├── deepagents.toml ├── AGENTS.md └── subagents/ ├── researcher/ │ ├── deepagents.toml # name, description, optional model override │ ├── AGENTS.md # subagent system prompt │ ├── skills/ # optional — subagent-specific skills │ │ └── analyze-market/ │ │ └── SKILL.md │ └── mcp.json # optional — HTTP/SSE MCP tools └── writer/ ├── deepagents.toml └── AGENTS.md ``` Each subagent subdirectory **must** contain: | File | Purpose | | ----------------- | ------------------------------------------------------------- | | `deepagents.toml` | Subagent config with `[agent].name` and `[agent].description` | | `AGENTS.md` | System prompt for the subagent | Each subagent subdirectory **may** contain: | File | Purpose | | ---------- | ----------------------------------------------------------- | | `skills/` | Subagent-specific skills (with `SKILL.md` files) | | `mcp.json` | MCP server configuration (HTTP/SSE only; stdio is rejected) | ### Subagent configuration Unique identifier for the subagent. Must be unique across all subagents. What this subagent does. The main agent uses this to decide when to delegate. Must be non-empty. Model override in `provider:model` format. Omit to inherit the main agent's model. ```toml subagents/researcher/deepagents.toml theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} [agent] name = "researcher" description = "Researches market trends, competitors, and target audiences" model = "google_genai:gemini-3.1-pro-preview" ``` ### Inheritance Subagents inherit some properties from the main agent by default: | Property | Inherited | Notes | | -------- | --------- | ------------------------------------------------------------ | | Model | Yes | Override with `model` in the subagent's `deepagents.toml` | | Tools | Yes | Override by adding `mcp.json` to the subagent directory | | Skills | No | Declare explicitly in the subagent's own `skills/` directory | ### Memory isolation Each subagent gets a dedicated, isolated memory namespace at `/memories/subagents//`. The subagent's `AGENTS.md` and skills are seeded into this namespace at deploy time. | Path | Main agent | Subagent | | ------------------------------- | ------------ | ------------ | | `/memories/AGENTS.md` | Read | No access | | `/memories/skills/**` | Read | No access | | `/memories/user/**` | Read + Write | No access | | `/memories/subagents//**` | Read | Read + Write | ### Example A go-to-market agent that delegates research to a specialized subagent: ```toml deepagents.toml theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} [agent] name = "gtm-strategist" model = "google_genai:gemini-3.1-pro-preview" ``` ```toml subagents/researcher/deepagents.toml theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} [agent] name = "researcher" description = "Researches market trends, competitors, and target audiences to inform GTM strategy" model = "google_genai:gemini-3.1-pro-preview" ``` ```markdown subagents/researcher/AGENTS.md theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} # Market Researcher You are a market research specialist. Your job is to gather and synthesize market data to support go-to-market decisions. ## Focus Areas - Market sizing: TAM, SAM, SOM estimates - Competitor analysis: product positioning, pricing, market share - Audience segmentation: demographics, psychographics, buying behavior ``` ## Limitations * **MCP: HTTP/SSE only.** Stdio transports are rejected at bundle time. * **No custom Python tools.** Use MCP servers to expose custom tool logic. ***
[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers. [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).