Is AI integrated in the ERPNext natively? And if there are any plans to do so?

Hi Frappe/ERPNext Community,

I’m exploring ERPNext and have a quick question:

Is there any native AI integration in the current version (e.g., v15 or upcoming v16) for features like predictive analytics, chatbots, or automated workflows?

I’ve noticed tools like Raven AI and community prototypes like the “ERP Agent,” but I’d like to confirm if these are core or external.

Also, are there any plans from the Frappe team to integrate AI natively in the future, given the growing demand and competitor advancements? Any insights would be greatly appreciated!

Thanks in advance!

Hi, yes, work is being done on this. Right now everything is still at an early stage of development.

Here are some relevant links that show what’s in progress:

2 Likes

Is there any progress further on this?

No, not as far as I can tell.

1 Like

Hi @samy4sam

It seems according to this blog they are not jumping on the AI Bandwagon yet

Raven is now a part of the Frappe product stack - and yes- our future plan includes enhancing its AI capabilities. So Frappe is still experimenting with AI - we haven’t found a lot of useful use cases though. With Raven’s function builder you can configure chat bots to serve your use case.

2 Likes

I think the way Basecamp went, by creating a CLI is super interesting: Basecamp — Basecamp CLI and Agent Skill: Agent first, agent native

Basically making Basecamp Coding Agent Compatible. With this you could do things like: “create a project starting on xx, fill description, create tasks and so on.” I believe this would actually be helpful for users to setup things. Of course you can also do read actions and so on. The interesting part is it can be easily used with Agents since they work well with CLIs

1 Like

In our internal AI testing, we consistently run into three core issues:

1. Permissions / Approval AI bots need write permissions to be truly useful. At the same time, you have to prevent scenarios where, say, all customers get deleted in one go. This is solvable with robust safeguards and approval workflows, and it’s arguably the easiest of the three problems.

2. Hosting / Data Protection It would be contradictory for an open-source ERP, one that exists precisely to avoid vendor lock-in and strengthen digital sovereignty, to depend on a closed, potentially insecure AI API. That said, this is becoming less of an issue as open-source AI models mature and local/self-hosted inference becomes more viable.

3. Validation / Client-Side Logic (the real deal-breaker) The biggest problem, in my view, is that far too much logic in Frappe apps lives on the client side. Validation, calculations, and various business rules are often executed in the browser rather than on the server. None of that is visible to an AI bot operating through the API.

Even for relatively simple tasks, like creating a purchase invoice and having the correct VAT rates or price rules applied, this becomes a serious obstacle. The bot calls the server-side API, but the logic that would normally fire in the browser never runs.

This is deeply rooted in Frappe’s architecture and, for me, it’s the actual deal-breaker for generic AI integration. You end up having to build separate backend interfaces for every doctype an AI bot needs to handle. And every time ERPNext or Frappe is updated, you risk having to adapt those backend workarounds to match whatever changed in the client-side code.

The Basecamp CLI approach that @Benema mentioned is interesting, but it works precisely because Basecamp’s operations are well-defined through a clean API. In Frappe’s case, the gap between what the API exposes and what actually happens in the browser is the fundamental challenge that needs to be addressed first.

@nikkothari22 I’d be curious to hear your perspective on this. Do you see the same challenges, especially around client-side logic being invisible to AI bots? From where we stand, the only realistic path forward for problem 3 would be for Frappe itself to provide a dedicated, server-side API layer that AI bots can work against, one that includes all the validation and business logic that currently only runs in the browser. Is something like that on the roadmap, or at least being considered?

1 Like

This will carry Frappe to so many process. implementing AI now is mandatory but if not take it with high responsibility, will make so many concern Security concerns , Budget concerns, Depending on external AI will not be easy at all which equal make it in house but I think they will inspire us as usual

All validations and calculations should ideally be implemented on the backend - frontend validations are just for UX - nothing else. If a Doctype/feature only has validations on the frontend, then that’s incorrect - whether you want to use it with AI or not. Users should not be able to bypass validations and calculations even if they create documents via APIs. So this needs to be fixed wherever applicable in ERPNext and other Frappe apps.

AI agents can consume standard APIs just like any other application. On Raven, AI agents can only access documents and fields that the user using the agent has access to so permissions are handled automatically - the functions and tool calls available to agents are permission scoped.

1 Like