Flow

bench get-app https://github.com/frappe/flow

[![Listed on Frappe Gems](https://frappegems.com/api/method/frappe_gems.seo.badge?app=frappe%2Fflow)](https://frappegems.com/gems/apps/frappe/flow)

--- Flow puts an AI assistant inside your Frappe site. It knows your DocTypes, respects your permissions, and can operate your site in plain English — creating records, sending emails, building DocTypes, creating agents and tools, and setting up RAG chatbots. **Set up a support agent:** > *"Create an agent that resolves customer support issues. It should use the Support Ticket doctype and these files as its knowledge: [attach files]"* Flow sets up the RAG pipeline, embeds and indexes the files, and keeps the DocType source in sync — automatically. **Put reporting on autopilot:** > *"Every weekday at 9am, email me a summary of yesterday's new leads with their contact details and source."* **Do anything a user can do:** > *"Find all overdue sales orders from last month and mark them as closed."* --- ## Framework Flow also ships as a Python framework for building agents in code. ### DocTypes | DocType | Purpose | | --- | --- | | `AI Provider` | Provider-level credentials and endpoint settings | | `AI Model` | Model configuration — set a `model_id` like `anthropic/claude-sonnet-4-6` | | `AI Tool` | Reusable tools, defined as a module path or inline script | | `AI Agent` | Instructions, model, and tools — configurable from the Desk or in code | | `AI Trigger` | Run an agent on a DocType event or a schedule | | `AI Knowledge Base` / `AI Knowledge Source` | Knowledge sources (files, URLs, DocTypes) for retrieval-augmented answers | | `AI Session` / `AI Run` | Persisted conversations and execution history | ### Define a tool ```python import frappe from flow import tool @tool def get_open_todos(allocated_to: str) -> list[dict]: """List open ToDo items for a user.""" return frappe.get_list( "ToDo", filters={"allocated_to": allocated_to, "status": "Open"}, fields=["name", "description", "status"], ) ``` ### Run an agent ```python from flow import Agent agent = Agent( model="anthropic/claude-sonnet-4-6", instructions="You help with Frappe tasks.", tools=[get_open_todos], ) result = agent.run("List open ToDo items assigned to me") print(result.output) ``` ### Persist a conversation ```python session = agent.new_session(title="Todo assistant") session.chat("What tasks do I have open?") session.chat("Close the ones due before last Friday.") ``` Every turn is saved as an `AI Run` linked to the session — so conversation history, tool calls, and outputs are all in the database. ### Built-in tools | Tool | What it does | | --- | --- | | `find_doctypes` | Search for DocTypes by name or module | | `describe` | Get the fields, filters, and available actions for a DocType or record | | `read` | Fetch records from any DocType | | `create` | Create one or more records | | `update` | Update fields across multiple records at once | | `delete` | Delete records | | `run_action` | Call a whitelisted method or workflow action on a record | | `execute` | Run arbitrary Python in a sandboxed context | Tool calls can require human confirmation before executing, and every run is persisted for audit. --- ## Installation Install into an existing [bench](https://github.com/frappe/bench): ```bash cd $PATH_TO_YOUR_BENCH bench get-app https://github.com/frappe/flow.git bench --site site-name install-app flow ``` Then add an `AI Provider` with your API key and an `AI Model` with a model ID such as `anthropic/claude-sonnet-4-6`, and open the Desk AI panel to start. For local providers like Ollama or LM Studio, set `Base URL` on the provider or model. ## License [GNU AGPLv3](license.txt)