# Support of many projects using single agent with Rasa 1.0

**URL:** <https://forum.rasa.com/t/support-of-many-projects-using-single-agent-with-rasa-1-0/10176>\
**Category:** Rasa Open Source\
**Created:** [May 22, 2019, 2:42pm UTC](https://forum.rasa.com/t/support-of-many-projects-using-single-agent-with-rasa-1-0/10176 "2019-05-22T14:42:51Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Omar](https://avatars.discourse-cdn.com/v4/letter/o/f0a364/32.png) [@Omar](https://forum.rasa.com/u/Omar)\
**Post date:** [May 22, 2019, 2:42pm UTC](https://forum.rasa.com/t/support-of-many-projects-using-single-agent-with-rasa-1-0/10176/1 "2019-05-22T14:42:51Z")

</div>

Hi All,

We are doing the migration of two agents dialgoflow to RASA.

With rasa nlu 0.15 we was able to train multiple nlu models for the same agent (using --project option)

With rasa 1.0 I didn’t find how to do that and maybe it’s not supported in the new version of rasa.

\*Before: python -m rasa\_nlu.train --config config\_rasa.yml --data training\_data\_toto.json --project toto

\*Now: rasa train nlu -c config\_rasa.yml -u training\_data\_toto.json (we can’t specify the project)

Could someone help us to know how to manage many models with the same agent.

Thanks, Omar

---

<div class="post-metadata">

**Author:** ![Tanja](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/tanja/32/4696_2.png) [@Tanja](https://forum.rasa.com/u/Tanja)\
**Post date:** [May 23, 2019, 10:54am UTC](https://forum.rasa.com/t/support-of-many-projects-using-single-agent-with-rasa-1-0/10176/2 "2019-05-23T10:54:37Z")

</div>

Hi @Omar, great that you are looking into Rasa 1.0!

Yes, in Rasa 1.0 we removed projects. We wrote a post a couple of weeks ago on that decision: [Removing projects for Rasa NLU server](http://forum.rasa.com/t/removing-projects-for-rasa-nlu-server/8962). Feel free to comment with your feedback.

With Rasa 1.0 an agent can just have one model loaded at a time. If you are running a Rasa server, you can replace the loaded model of an agent by calling `PUT /model` (see [https://rasa.com/docs/rasa/api/http-api/#tag/Model/paths/~1model/put](https://rasa.com/docs/rasa/api/http-api/#tag/Model/paths/~1model/put)). So you can either load the desired model before answering a request or you can run two Rasa servers - one for each model. As this solution might not be optimal, we are still collecting feedback. So, please share your thoughts 🙂