frappe

otto: Add LLM-Powered Automation to Frappe Apps

Otto is an experimental Frappe app and Python library for connecting language models to Frappe workflows. It supports task automation, custom assistants, tool use, and resumable LLM sessions.

PythonAGPL-3.0AILLMAutomation
View on GitHub Compare
Stars
81
Forks
23
Stars, last 30 days
+0

Our take

Health score

16/100

How it is scored
Activity
19
Community
4
Issues
21
Pull requests
20

+0 stars in the last 30 days

  • Fewer contributors than 91% of the projects we track

Project history

Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.

Selected snapshot

Stars

81

Forks

24

Change since Nov 16, 2026: 0 stars·0 forks

Overview

Otto is a Frappe Framework app and library for adding LLM interactions and automation to Frappe applications. It provides a way to define tasks that run manually or in response to document lifecycle events, and to build custom assistants over Frappe apps.

It is intended for Frappe developers who want to experiment with LLM-backed workflows or use Otto's library directly in their own apps. The project is explicitly in an early, experimental stage.

Key Features

  • Define automated tasks tied to Frappe document types and lifecycle events.
  • Configure available LLMs and API keys through Frappe doctypes.
  • Define tools that tasks can use, including a server-script-like execution environment.
  • Create and resume LLM sessions, with streaming or non-streaming interaction.
  • Track task runs as executions and inspect interactions in a session viewer.
  • Use the library independently in a Frappe app to manage LLM sessions and tool calls.

Use Cases

  • Frappe developers can automate routine handling of documents, such as generating a response to a support ticket.
  • App teams can build assistants that answer questions using information available in their Frappe applications.
  • Developers can prototype model-backed workflows that trigger manually or when a document event occurs.
  • Teams integrating LLMs into a Frappe app can use the library to manage sessions, streaming responses, and tool-use updates.

Getting Started

In a configured Frappe bench directory, install the app with:

bench get-app otto --branch develop
bench --site site-name install-app otto

See the repository README and library documentation for setup and usage details.

Alternatives

  • griptape: Griptape builds general-purpose AI tasks, agents, and pipelines, while Otto focuses on connecting LLMs to Frappe workflows.
  • lagent: Lagent is a general framework for building LLM agents and multi-agent applications, rather than an integration focused on Frappe workflows.
ProjectLanguageLicenseStarsStatus
ottoPythonAGPL-3.081Not checked yet
griptapePythonApache-2.02.6kActive
lagentPythonApache-2.02.3kQuiet

Considerations

Otto is in very early development, and its application features are still under experimentation. The README does not recommend using it as a mature application, though it can be tried as a library within a Frappe app. Using it requires a Frappe bench and site, plus API keys for the models you configure. The repository is licensed under AGPL-3.0.

Found this useful?

Share it with someone who would like otto.

Comparisons