Backend integrations
Browse available filesystem backends for Deep Agents or contribute your own to the ecosystem. Learn more about how backends work in the backends docs.
Integration components
- Typical retrieval flow: Document loaders → Text splitters → Embedding models → Vector stores → Retrievers → Chat models
- Agent capabilities: Tools, Middleware
- Execution and state: Sandboxes, Backends (this page), Checkpointers, Stores
Share your backend
Custom backends connect Deep Agents to storage systems such as databases, object stores, and virtual filesystems. Share yours with the community:
Follow the custom backends guide to build your own backend.
Open a PR to the docs repo to add your backend to the table below.
All backends
| Backend | Description | Package | Source |
|---|---|---|---|
| Azure Blob Backend | Azure Blob Storage implementation of the Deep Agents BackendProtocol. Persist agent workspace files, memories, and artifacts in a blob container. | langchain-azure-storage | langchain-ai/langchain-azure |
| MongoDB VFS Adapter | Virtual filesystem backend backed by MongoDB Atlas. Persist agent files, including memories, artifacts, and conversation history, in a MongoDB collection. | langchain-mongodb-deepagents-vfs | langchain-ai/langchain-mongodb |
Have a backend to share? Open a PR to add it here.
Info
If you'd like to contribute an integration, see Contributing integrations.