Realm
Infra for personalized social media.
The problem Realm solves
Problem Statement
Everyone on social media is stuck in the doomscrolling loop. They are not able to find the content that is relevant and provide value to them.
Why does this problem exist?
Lack of personalization and context in the content that is being consumed.
What are the possible solutions to this problem?
The generic solution to this is to ask user to define their interests and preferences, and then based on that, the content is personalized.
But this is not a good or scalable solution. No one has time to define their interests or select the option to "Not Interested".
Solution: Realm
Realm is the AI powered infra for providing personalized experience to users on any social media platform.
How does Realm solve the problem?
Realm uses AI intelligence to understand users' post and its intent, and create a rich contextual graph for every user.
This contextual graph can be utilized by any social media application to provide personalized content to their users.
Implementations
We have created two implementations to showcase the power of personalized social graph created by Realm.
ReplyGuy
ReplyGuy is a simple agent, powered by Realm, which comments on your posts on Farcaster with other relevant posts as per the content you mentioned.
We got 360+ users within a week of launch and served 16K+ replies.
Demo || Live Link || Source Code
FarSearch
FarSearch is a ChatGPT like interface, powered by Realm, which can be used to search any content on Farcaster.
How does Realm work?
Realm fetches real-time content on Farcaster and analyzes the content to create a personalized graph for the user.
Tech Stack
- Neynar APIs for fetching content from Farcaster.
- Eigen Layer AVS on Base and Ethereum.
- Gemini and OpenAI for generating embeddings.
- Supabase for storing the data.
Contracts
The following AVS contracts have been deployed on Base Sepolia (L2) and Ethereum Holesky (L1):
NOTE
- We have deployed AVS on the Base Sepolia and Ethereum Sepolia testnet, due to the cost and setup of the reward distribution mechanism for validators.
- The only open source repo is for ReplyGuy: https://github.com/Hojaeaga/replyguy
- If you like to access any of the private repos, please reach out to us at Telegram @megabyte0x or [email protected].
Roadmap
We have big vision for Realm. Currently, we are using Farcaster social graph but working on to expand to other social media platforms like Telegram, X, and more.
The cross-platform social graph will be a game changer and will help us to provide the best personalized experience to users on any social media platform.
What are we looking for?
We are actively raising funds to build the scalable and robust infrastructure for Realm.
Contact Us
If you have any questions or want to discuss the project, feel free to reach out to us at Telegram @megabyte0x or [email protected].
Challenges we ran into
After building the base infra (Realm), we launched an application on top of it, ReplyGuy, a simple agent which comments on your posts with the other relevant posts as per the content mentioned.
In starting, we were happy with the responses from the AI and in getting our first 120 Subscribers.
Link: https://warpcast.com/yourreplyguy/0xa9cfb518
But when we looked for the feedback from the users, we found two major issues:
The reply frequency was really high.
Sometimes the reply was not relevant to the post.
So we sat, screamed through the night and came up with the following solution:
Conditional reply based on the post.
Examples:
If the post is just a reply to some other post or any empty quote post, then don't reply.
If the post is in a channel, prioritise the content discovery from the channel.
Another issue was verifying that the data is being fetched from the trusted servers and replies are being generated by the AI and doesn't have any human intervention.
To fix this, we came up with the following solution:
Verifiable Agent using Eigen Layer.
We built an Eigen Layer AVS on Base and Ethereum to verify the data and the replies posted by the agent, using Reclaim Protocol and Othentic stack.
Tracks Applied (3)
AI
Mini-apps
Consumer
Technologies used
Cheer Project
Cheering for a project means supporting a project you like with as little as 0.0025 ETH. Right now, you can Cheer using ETH on Arbitrum, Optimism and Base.