---
title: Customization
description: DeerFlow's pluggable architecture means most parts of the system can be replaced or extended without forking the core. This page maps the extension points and explains how to use each one.
---

import { Callout, Cards } from "nextra/components";

# Customization

<Callout type="info" emoji="🔧">
  DeerFlow is designed to be adapted. You can extend agent behavior by writing
  custom middlewares, adding new tools, building skill packs, and replacing any
  built-in component through the config.yaml <code>use:</code> field.
</Callout>

DeerFlow's pluggable architecture means most parts of the system can be replaced or extended without forking the core. This page maps the extension points and explains how to use each one.

## Custom middlewares

Middlewares are the primary extension point for adding behavior to the Lead Agent. They wrap every LLM turn and can read and modify the agent's state before or after the model call.

To add a custom middleware:

1. Implement the `AgentMiddleware` interface from `langchain.agents.middleware`.
2. Pass your middleware to the `custom_middlewares` parameter when building the agent.

```python
from langchain.agents.middleware import AgentMiddleware
from deerflow.agents.thread_state import ThreadState

class AuditMiddleware(AgentMiddleware):
    async def on_start(self, state: ThreadState, config):
        # Runs before each model call
        print(f"[audit] turn starts: {len(state.messages)} messages in context")
        return state, config

    async def on_end(self, state: ThreadState, config):
        # Runs after each model call
        print(f"[audit] turn ends: last message type = {state.messages[-1].type}")
        return state, config
```

Custom middlewares are injected into the chain immediately before `ClarificationMiddleware`, which always runs last.

## Custom tools

Add new tools to the agent by registering them in `config.yaml` under `tools:`:

```yaml
tools:
  - use: mypackage.tools:my_custom_tool
    api_key: $MY_TOOL_API_KEY
```

Your tool must be a LangChain `BaseTool` or a function decorated with `@tool`. It will be instantiated using the `use:` class path and any additional fields from the config entry.

For community-style tools, the pattern is a module-level function or class that returns a `BaseTool`:

```python
# mypackage/tools.py
from langchain_core.tools import tool

@tool
def my_custom_tool(query: str) -> str:
    """Search my custom data source."""
    return do_search(query)
```

## Custom sandbox provider

The sandbox can be replaced by implementing the `SandboxProvider` interface:

```python
from deerflow.sandbox.sandbox_provider import SandboxProvider
from deerflow.sandbox.sandbox import Sandbox

class MyCustomSandboxProvider(SandboxProvider):
    def acquire(self, thread_id: str | None = None) -> str:
        # Return a sandbox_id
        ...

    def get(self, sandbox_id: str) -> Sandbox | None:
        # Return the sandbox instance for this id
        ...

    def release(self, sandbox_id: str) -> None:
        # Cleanup
        ...
```

Then reference it in `config.yaml`:

```yaml
sandbox:
  use: mypackage.sandbox:MyCustomSandboxProvider
```

## Custom memory storage

Replace the file-based memory with any persistent store by implementing `MemoryStorage`:

```python
from deerflow.agents.memory.storage import MemoryStorage
from typing import Any

class RedisMemoryStorage(MemoryStorage):
    def load(self, agent_name: str | None = None) -> dict[str, Any]:
        ...

    def reload(self, agent_name: str | None = None) -> dict[str, Any]:
        ...

    def save(self, memory_data: dict[str, Any], agent_name: str | None = None) -> bool:
        ...
```

Configure it in `config.yaml`:

```yaml
memory:
  storage_class: mypackage.storage:RedisMemoryStorage
```

## Custom skills

Skills are the easiest extension point. Create a directory under `skills/custom/your-skill-name/` with a `SKILL.md` file. The skill is discovered automatically on the next `load_skills()` call.

See [Skills](/docs/harness/skills) for the full directory structure and `SKILL.md` format.

## Custom models

Any LangChain-compatible chat model can be used by specifying it in the `use:` field:

```yaml
models:
  - name: my-custom-model
    use: mypackage.models:MyCustomChatModel
    # Any extra fields are passed as kwargs to the constructor
    base_url: http://my-model-server:8080
    api_key: $MY_MODEL_API_KEY
```

The model class must implement the LangChain `BaseChatModel` interface.

## Custom checkpointer

Thread state persistence can use any LangGraph-compatible checkpointer:

```yaml
checkpointer:
  type: sqlite
  connection_string: ./my-checkpoints.db
```

For custom backends, implement the LangGraph `BaseCheckpointSaver` interface and configure it programmatically when initializing the `DeerFlowClient`.

## Guardrails

Add pre-execution authorization for tool calls through the `guardrails:` config:

```yaml
guardrails:
  enabled: true
  provider:
    use: deerflow.guardrails.builtin:AllowlistProvider
    config:
      denied_tools: ["bash", "write_file"]
```

For custom guardrail logic, implement a class with `evaluate()` and `aevaluate()` methods and reference it via `use:`.

<Cards num={2}>
  <Cards.Card title="Integration Guide" href="/docs/harness/integration-guide" />
  <Cards.Card title="Configuration" href="/docs/harness/configuration" />
</Cards>