Proposed by:
Requested amount:
0 DOT

#1343 · dAppForge Milestone 3

1. Project

1.1 Summary of Important Points

We submitted a previous treasury proposal, ref 985, and completed all the tasks/milestones.

Milestone 2 of dAppForge V1 is now completed. Here are some videos that show what you can do with the plug-in:

Here is our GitHub: https://github.com/dappforge

Currently, the plug-in can be used for code generation and autocompletion for substrate and ink! The plug-in does a good job of providing insights into the code generated, which helps developers increase their understanding of substrate/ink. With every fine-tuned version, developers should be able to build/code better and faster. This will lead to more applications being built on Polkadot.

We have now completed 2 of the 4 milestones to build dAppForge V 1.0. To recap, these are the 4 milestones:

  • Milestone 1 (completed): the first iteration of LLM ( substrate only) and the VS code plugin alpha version. This was completed, but the product is at a level where developers won’t see a lot of value. This is because the model needs to be further fine-tuned.
  • Milestone 2 (completed: ref 985): The product's beta version. It includes a fine-tuned LLM model for substrate, integrated ink!, and a chat feature.
  • Milestone 3 ( current treasury proposal): These are the main points ( more details in section 1.6):
    • Fine-tune llm for substrate and ink! further. This will help developers increase their understanding of both substrate/ink!, which will lead them to code faster and reduce development time.
    • Integrate Solidity. This will set the foundation for helping developers deploy EVM smart contracts on Asset Hub when Plazza is finished in Q2 2025. Polkadot needs more dApps, and one strategy is to make it easier for solidity developers to deploy on Asset Hub.
    • Develop and integrate a monetization strategy to support the product's growth, focusing on a two-tier pricing structure, initial freemium experience, and scalable subscription option ($30/month). The paid tier will give developers access to enhanced AI, providing more accurate and contextually relevant code suggestions. We will also build a specialized educational subscription track focused on onboarding users to learn using Substrate and Ink!

      • dAppForge is open-sourced. Anyone can clone the AI model and run it on their machines. However, you will need to set up your cloud infrastructure to run the model. If you don’t want to manage your own infrastructure, there will be a free tier for you to use.

    • Develop a knowledge graph focused on the Rust programming language, capturing comprehensive insights on Rust syntax, libraries, frameworks, best practices, and common patterns. This will be crucial to expanding our reach to the wider Rust developer community. It will also create an opportunity to onboard them into the Polkadot ecosystem by demonstrating how their existing skills can be used to build blockchain applications using substrate/ink! Here are some examples:
      • Upon starting a new project, the plug-in offers a dropdown option: "Would you like to try building a decentralized application using Ink!?" or “Would you like to explore how to build your blockchain using substrate?”
        • Once JAM is live, we expect Rust developers to write contracts in Rust that would be compiled with PVM.  We also expect rust to be used to write different JAM services in the future. 
  • Milestone 4 ( future treasury proposal): These are the main points:
    • Fine-tune current knowledge graphs.
    • Enable Ink! and Solidity developers to deploy their smart contracts to Asset Hub. This involves making sure the contracts correctly compile to PVM. 
    • Implement more features for the paid tiers, such as:
      • Personalized Learning: Train the AI on your codebase for tailored suggestions.
      • Up-to-date Knowledge Graph: Access the latest Polkadot knowledge and best practices with our regularly updated knowledge graph.

1.2 Overview

Tagline: AI-powered plug-in for Polkadot developers that reduces development time.

Brief description: Building on Polkadot is complex, creating a high barrier to entry. dAppForge aims to enable Polkadot developers to build better dApps, appchains, and parachains faster, lowering the entry barriers for new developers. The AI model is currently trained on Substrate and ink!. The model can used for code generation and autocompletion for substrate and ink! It provides insights into the code generated, which helps developers increase their understanding of substrate/ink. We will now also integrate solidity to enable developers to deploy EVM smart contracts on Asset Hub when Plazza is completed in Q2 2025.

Motivation: Substrate and ink! can build great parachains, appchains, and dApps, attracting millions of users, which is crucial for the blockchain industry. Polkadot has the second-largest developer ecosystem and consistent growth in developer activity. dAppForge aims to empower existing developers and make it easier for new developers to join and build on Polkadot. Additionally, including solidity will make it even easier for developers to deploy their smart contracts on Asset Hub.

Here is the rest of the proposal: 

Read more
StatusDeciding · 27d
99%Aye
Aye (3)
20.054K DOT
Nay (1)
5 DOT
Decision0 / 28d
0.0%37.0%
29.6%Support Threshold
0Support Threshold
Support(0.00%)
≈ 10.011K DOT
Issuance
≈ 1.51B DOT
Vote
Christian123Dec 9
saxemberg

Hello and thank you for the contributions. The progress in this tool has been impressive. Sometimes the fine tuning is not enough for these architectures but the team in charge of the tool knows what's its doing  and what it needs to be included in the dataset so kudos for that,

Some additions and nice to haves like independence from Github, easy to use alternatives to AWS among others that have already mentioned and are in the pipeline is something we would also would like to see.

We are starting to push for more comprehensive and explicit details of future support and flexibility in the inclusion of new features. For the latter it's clear that requested features have been considered and added already. For the latter we would like to know also if the maintenance of the tool has been considered and for how long. We can already see your commitment to the new developments but this is something we’ll start checking on all referenda from now onward.

Thank you, @saxemberg, for your feedback! Here are some comments 

"Some additions and nice to haves like independence from Github, easy to use alternatives to AWS among others that have already mentioned and are in the pipeline is something we would also would like to see." --> Yes, we agree. 

"For the latter, we would like to know also if the maintenance of the tool has been considered and for how long." --> The goal is for the product to become self-sustainable after completing Milestone 4. Regarding the timeline, we expect Milestone 4 to be completed around August 2025. 

Thank you again for your feedback! 

saxembergDec 9

Hello and thank you for the contributions. The progress in this tool has been impressive. Sometimes the fine tuning is not enough for these architectures but the team in charge of the tool knows what's its doing  and what it needs to be included in the dataset so kudos for that,

Some additions and nice to haves like independence from Github, easy to use alternatives to AWS among others that have already mentioned and are in the pipeline is something we would also would like to see.

We are starting to push for more comprehensive and explicit details of future support and flexibility in the inclusion of new features. For the latter it's clear that requested features have been considered and added already. For the latter we would like to know also if the maintenance of the tool has been considered and for how long. We can already see your commitment to the new developments but this is something we’ll start checking on all referenda from now onward.

0abeccb9f6bb43f385af6ac9aDec 9

dAppForge is a huge win for substrate and polkadot tech ecosystem.

I have been following this project since I met Christian in HK and the direction this project hast taken is the right one. The team behind this project has completed each milestone on time, and you can really tell this is the way to go (open source + open beta) after using the tool, which still has some things to iron out, but that's the main goal of this proposal.

All in all, the team behind this is working great, the details described here are complete and I have no doubts this is a project that could help not only the development experience but the polkadot innovation quota itself as well.

Thank you Christian, and keep it up! 💪

jaypopatDec 8

Kudos to Christian and his team for accomplishing these milestones! It's transformed my Polkadot development workflow, slashing coding time and simplifying complex tasks. Fully support this proposal and looking forward to seeing the solidity integration with the arrival of Plaza

jaypopatDec 8

[Deleted]

MrishoLukambaDec 6

So, in substrate most of errors are a result of macros, And TBH in Rust macros are the WORST in debugging, consumes time and leads to slower development speed.
Christian works tirelessly to ensure the experience in the best blockchain framework to be smoother. 

As newer teams in Polkadot, Ethereum, Cardano use Substrate, DappForge is solving an integral problem to make the development circle short.

I support this because it is a leverage for us developers and you should too.

PolkaWarriorDec 6

Chris and team had done phenomenal  job in building dAppForge. I am also happy to know that they made it opensource . This new proposal milestones seems interesting and can improve developer experience substantially. Look forward to see more great stuff coming from dAppForge. All the best team !

GemmaDec 5

One of the greatest challenges in our industry is reducing friction for both developers and users, alongside overcoming the steep learning curve many face.

dAppForge is tackling this head-on by revolutionizing speed and efficiency for experienced Substrate, and ink! developers, while simplifying onboarding for newcomers to the ecosystem—many of whom transition from Solidity to Rust, Substrate, and ink!

With dAppForge, developers can simply write a prompt and instantly receive boilerplate code for pallets and ink! smart contracts, complete with tests, code explanations, and auto-generated documentation. This not only accelerates the development process to lightning-fast speeds but also significantly smooths the learning curve for everyone.

Kudos to the team for this fantastic achievement! 👏

gunjanDec 5

This is a fantastic application that's evolving rapidly! Big congratulations to Team Christian! I had the chance to test it, and it's already quite impressive at this stage. I really appreciate how Chris takes feedback positively and works on it with such enthusiasm. I fully support this proposal and am excited to see it progress further and contribute meaningfully to the Polkadot ecosystem!

Peter_R0GUEDec 4

It’s been great to see the progress dAppForge has made. Having played around with early versions, this current version is miles ahead, generating code much faster (even though still in beta), more accurate for both Substrate and ink!, and the UX of using it is now greatly improved as well. I know they’ve had to work through struggles of outdated docs and examples get proper output. Excited to see it further grow!

munificentDec 2

nice job by the team so far, let's bring it home :)

noahjoerisDec 1

Awesome proposal! Loving the progress on dAppForge so far :) The milestones you’ve outlined to enhance functionality and make the DX smoother are spot on. Excited to see this grow.

daiagiNov 30

writing in substrate is no easy task.
I appreciate the work dAppForge is done and doing in order to reduce this barrier to entry, hopefully enriching the ecosystem with high quality applications in the near future

altimarioNov 29

Christian and his team have consistently delivered on their promises with dedication and competence. Each milestone makes Dappforge better and better. Their hard work deserves our support to help them reach future milestones. Best wishes and good luck with the next steps!

SouravNov 29

dAppForge has come a long way since its inception and I have already stopped using copilot for Substrate. It's super efficient and generated complicated code with ease. There have only been improvements and it has made my Substrate development easier. It has now become an integral tool in my arsenal. The suggestions are super accurate and I cannot wait to see how far the team takes it! 

yhamacnyNov 28

Thank you for embarking on this journey and creating this product!

To be frank, it’s not perfect—but that’s to be expected for a beta. That said, it’s already miles ahead of Google or GitHub code search in terms of delivering prompt, meaningful, and useful answers. Beyond that, it has proven to be an incredible educational tool right out of the box. I was genuinely blown away by the capabilities of the test versions, which significantly accelerated my development time.

Wishing you and the team smooth sailing ahead—I can’t wait to see the quality and innovation delivered in the upcoming RCs and GAs!

celadariNov 28

I want to take a moment to highlight the substantial work Christian and his team have accomplished with dAppForge.

  • Training a full model on Substrate and ink! is no small feat—it’s a challenging process, from gathering enough high-quality training data to fine-tuning the model effectively. What they’re building is truly unique: a Polkadot-specific, fine-tuned AI model, not just another wrapper around ChatGPT. This deserves recognition by the community.

 

  • Additionally, assembling a strong team capable of tackling such complex tasks is no easy task—I can relate to this from my own experience with my venture. Christian has built a talented and capable team, and their results speak for themselves.

 

  • On our end, we see dAppForge being incredibly useful in a concrete way, especially as we’re actively using smart contracts and integrating pallets into our product. The smoother developer experience it offers is crucial—debugging and resolving compilation issues can be notoriously difficult, and dAppForge can significantly ease that process.
SupeluminalNov 28

As a Substrate developer, I appreciate the effort being made to simplify the onboarding process and enhance the developer experience. dAppForge is doing a good job in reducing barriers to entry for Substrate. I’m truly amazed by the progress they’ve achieved in just a few months!

KazunobuNov 26

I can't believe what the dAppForge's team has been able to accomplish for the past 2~3 months technically ➡ I already ditched Rust Analyzer for dAppForge, this is how good it got!! Can't wait to see this project grow further!

lukaNov 25

It's great that you're open sourcing the model and allowing others to run it locally. Looking forward to seeing how it works for solidity and how it compares to other LLMs. Well done on the milestones so far

Powered by Subsocial