pranav_rajs

Hi HN,

We built Faultline at Chatwoot to help our team debug infrastructure incidents faster. It's an AI agent you can ask questions in plain English — it autonomously queries your monitoring tools, cloud infrastructure, and codebase, then comes back with a root cause analysis.

It connects to New Relic, Sentry, AWS, GitHub, and PagerDuty using MCP (Model Context Protocol) servers and native integrations. You ask something like "Why is the API latency high?" and the agent loops through your tools — pulling APM metrics, checking error rates, scanning recent deploys — until it has enough data to give you an answer.

Stack: Rails 8 + Sidekiq backend, Python/FastAPI agent service using OpenAI, Vue 3 frontend, PostgreSQL, Redis. All integrations are configured through the UI, credentials encrypted at rest.

It doesn't replace an SRE — but it does the first pass of pulling data from five different dashboards and correlating timelines, which usually takes 10-15 minutes manually.

Demo: https://youtu.be/S1-pW_wD2uA

GitHub: https://github.com/chatwoot/faultline

Blog: https://faultline.chatwoot.com/blog/introducing-faultline

Would love your feedback.

This is brilliant. I'd probably add the notifications to download Chrome and ads in Google search to this experience.

Hey HN,

Thanks for all the support you folks gave us in the past[1]. At Chatwoot[2], we are developing an open-source[3] customer support platform as an alternative to Intercom and Zendesk. I'm glad to announce our latest AI update. We have been working with the latest LLMs to see if we can assist support staff in reducing their workload.

We have observed large-scale Chatwoot deployments with over 10 million messages. From our discussions with the teams handling these deployments, we noticed two types of queries. The first type consists of simple questions, sometimes with minor tweaks. The second type requires human intervention and typically involves more complex support queries. Many tools first employ an FAQ bot, now an AI bot, before transferring to a human. This process can be frustrating for both the user and the support agent. We have found that customers, especially when they are already frustrated, dislike having to interact with a bot before reaching a human to resolve their issue.

The issue we face is the lack of distinction between the two types of queries. Not all queries are inherently support queries. Sometimes, the customer may not want to search through the documentation, or the documentation may not be well-organized enough to find the answer. Having a chat common chat interface makes it harder for everyone.

We believe that a clear UX distinction can make a significant difference. Here is how we plan to split these conversations.

a/ *Universal search interface*: This is a Chat GPT-like chat that you can integrate into your application. Users can click on the search icon or use CMD+K to access it. They can find answers using your help desk articles and carry out tasks through natural language queries like "Where is my order?" or "When is the next billing date?". We have found this can improve the quality of support requests received.

b/ *Live Chat SDK*: To address complex issues, your customers can communicate directly with you with the live chat SDK.

This approach will clarify expectations for the end customer. Use the search function for straightforward queries and engage with an agent for more complicated ones.

Along with these, we also introduced some updates to the agent interface. These updates will help agents prioritize conversations by auto-tagging them and routing them to the appropriate teams.

We are launching it as a closed beta at the moment to work closely with teams with scale and unique problems. Also, we have not yet figured out how we can add support for the open-source LLMs in different environments, as our installations are one-click at the moment. Adding those would make it complex for everyone.

[1] https://news.ycombinator.com/item?id=26501527

[2] https://www.chatwoot.com

[3] https://github.com/chatwoot/chatwoot

Most people see this as some sort of tax to provide better support, which should not be the case. We need better tools at reasonable and transparent pricing. Hope we succeed in that mission.

Chatwoot is currently suited for support use cases. We are working on the customer success workflows (onboarding, retention etc) now. Hope it gets there soon.

Great feedback!

The FB/Instagram channels are a pain to manage (even for us) due to the app review cycle. This is a common problem in the community. Recently we have seen many rejections in Instagram API reviews without a specific reason. Some of the alternatives the Meta developer review team suggests are also not working. We are trying to make this flow better using a hosted app or something. Open to ideas here.

We are aware of the issues with the mobile app. It is getting a revamp now, hope most of the issues are resolved by it.

We are following open core model. The idea is to build a sustainable way to provide more value in opensource. Bulk of the features are under MIT license.

Help Center is available in Opensource edition. We have SSO, roles & permissions in the enterprise.

We have 2 versions of software. Enterprise edition and the community edition. The repository has a dual license. The /enterprise folder is licensed under a proprietary license whereas everything else is under MIT license

Hey folks,

We launched Chatwoot a couple of months back in HN and was well received by the community.

### What is Chatwoot?

Chatwoot is an open-source, self-hosted customer engagement suite, built as an alternative to Intercom and Zendesk. With Chatwoot, you can view and manage your customer data, communicate with them irrespective of which medium they use, and re-engage them based on their profile.

### What's new?

Today we are excited to make 3 major announcements:

1. 2.0 version

2.0 version ships with an updated dashboard that is completely redesigned for a better user experience. This update ships with many new features, including more communication channels, productivity enhancements, better conversations visibility, re-engagement options, etc.

2. Enterprise edition

We will include the features such as customisable dashboards, SLA Management, Agent scheduling software, IP blocklisting etc., suited for large organizations in the Enterprise Edition software. In contrast, Small and medium businesses would continue to use the Community edition. We are making the license update in the repository to include a dual licensing option.

3. Contributor Hall of Fame

The community has been core to our success so far. It is rewarding to see people from different countries and cultures come together for a common goal. Our product supports more than 30 languages right now, and all of it was contributed by the community. We want to honor and extend our gratitude to the people who have put the effort in helping us to make this software better every day. We would be publishing the contributor hall of fame.

Looking forward for your thoughts and feedback :)

Github sponsors work that way!

Handling separate closed fork is one of the solution. Historically, it is an overhead for the team managing the project. You can read about the experience shared by Metabase [0].

[0] https://www.metabase.com/blog/Opening-Metabase-Enterprise/in...

Nice to know!

> Chatwoot isn't a piece of cake to set it up

We are working on make it simpler. :D You will hear from us in the upcoming releases.

> Moreover, we are in the process of hiring and dedicating a small team who will contribute changes to Chatwoot and raise PRs upstream.

That's great to know.

We expect to follow Gitlab's path on this. There will be 2 repos. One with EE licensed code and the other one completely foss.

eg: Gitlab[0] vs Gitlab FOSS [1] code

[0] https://gitlab.com/gitlab-org/gitlab

[1] https://gitlab.com/gitlab-org/gitlab-foss

We intend to build an entire suite for customer engagement while giving the flexibility to customize it to match the business needs.

Papercups is a nice product. It's good to have multiple players in the open-source space.

Here are some of the thoughts which comes to my mind that differentiates Chatwoot from Papercups:

1. Omnichannel inbox [0]: Chatwoot let's you connect 7 different channels including email, whatsapp etc so that you have all your customer conversations in one place.

2. API Channel for building custom channels: Some people see Chatwoot as an alternative to Twilio Flex (except voice) as they could build custom channel using our API Channel and have the flexibility to customize the software to the extend they need.

3. Integration with Chatbot providers: Chatwoot has a concept of agent bots which allows you to connect with the existing Chatbot providers like Rasa.ai and Dialogflow easily. [1]

4. Shared inbox with teams: You can create a group of users under specific team and collaborate over a ticket. [2]

5. Flexibility to manage more than one brand under the same account. If the company has more than one product, instead of creating multiple accounts, the same account allows you to create different inboxes and set different permission levels for the users.

6. Availability of mobile apps on iOS and Android which helps you to chat with your customers on the go.

[0] https://www.chatwoot.com/features/channels

[1] https://www.chatwoot.com/features/chatbots

[2] https://www.chatwoot.com/features/shared-inbox

> like a tax if you take X% of my profit

I have heard this analogy from other users of Intercom also. This is definitely an interesting take. But yeah, I got your point. Let us know if you need some help setting Chatwoot up.

There was some issues with email continuity at that time. This is resolved and the docs for both continuity [0] and email channel [1] are updated.

Let us know if you need some help setting it up, our team will be happy to take a call.

[0] https://www.chatwoot.com/docs/conversation-continuity

[1] https://www.chatwoot.com/docs/self-hosted/email-setup

There are people who have built custom solutions on top of Chatwoot and selling it. There are people who are selling it in their country without changing the code and making profit out it. I'm happy to help those people out (not for free, would charge something obiviously). There are different markets where we might not be able to cater. Since the solution is flexible enough to build custom channels, I've seen people using it as "Whatsapp CRM for X country".

We are following the path Gitlab has taken. To sustain as a business, we will have some modules suited for large enterprises under an EE license, but it would not hinder the open-source part and the freedom that comes with it. If people want to build on Chatwoot, they will be free to do that.

It is multi-tenant, just like other SaaS providers. We can provide managed-services based on request.

Haha! for sure.

This is a hard decision to make. It would be considered on the basis of a couple of things. If it is derivate of already existing code, we would suggest not to do that. If it is an original work, then we would consider those.

Having said that, we want to reduce such kind of conflicts happening in the community. So we would try to limit an entire module under EE License rather a part of it.

Our community edition which is available with MIT license and is free for use should cover the starter plans in Intercom.

$99/user/month is targetted at large enterprises requiring enterprise support.

> If I may, what's your take on Cloudflare's upcoming DurableObjects for Workers [0] and the possibilities that entails for chat-applications like these?

It seems interesting. We have not had time yet to deep dive.

> I wanted to know if there are there any other models other than GitLab's that YC recommends to its startups?

We have not seen any trend emerging other than open-core so far.

> Also, curious why for-profit F/OSS startups would leave up a "sponsor" button on their GitHub. :D

Some one wants to support us without taking subscription plans is a great reason to have it.

> Tangential: Was this the startup that failed [2]? If so, it would be interesting to read your views on it since it looks like except the co-founder that blogged about the failure, the rest of the original founding team is back building chatwoot?

I think you might have misunderstood, op was mentioning another startup, not Chatwoot.

You can read our story here. https://www.chatwoot.com/blog/building-in-the-open

> Off-topic: If you are okay, can you reveal if you've raised funds from Indian Angles (many particularly active in the SaaS scene [3]) and what has been your experience so far? And a set of recommendations, if any, for other Indian F/OSS SaaS upstarts? May be you should blog about it?

We will definitely write about it soon.

Great! Just sent an email :)

We have had requests for phone support. At the moment, our primary focus is on text based messaging. We will get to the phone/video part in the future.

We want to make the software simple and easy to use. Setting up Asterisk and using it with Chatwoot was too much to handle. So we deferred that work for now. We will come back to it later.

We have a enterprise edition in works. We will launch it soon. Whatever is MIT now, will stay as MIT.

We know Preetam, they are a great team!

We are using Discord for managing our community. We have already thought about this. There was not enough requests to build the integration.

Anyway I have created an issue at the repo, so that this can be tracked. https://github.com/chatwoot/chatwoot/issues/1941