ARBuilder - Final Report

ARBuilder — Final Report

Project: ARBuilder — AI-Powered Development Assistant for the Arbitrum Ecosystem
Team: Quantum3 Labs
Grant Program: Arbitrum Foundation Developer Tooling
Period: January – March 2026
Milestones Completed: 5/5


1. Overview

ARBuilder is an open-source MCP (Model Context Protocol) server that provides AI-powered code generation for the Arbitrum ecosystem. It transforms natural language prompts into production-ready code for:

  • Stylus smart contracts (Rust/WASM) — SDK 0.10.0
  • Cross-chain bridging (ETH/ERC20 across L1, L2, L3)
  • Full-stack dApps (NestJS + Next.js + The Graph + Chainlink)
  • Orbit chain deployment (config, rollup, validators, node setup)

The tool uses a RAG (Retrieval-Augmented Generation) pipeline with hybrid BM25 + vector search over 40+ curated Arbitrum repositories, ensuring generated code follows current SDK patterns rather than relying on outdated LLM training data.

19 MCP tools work inside Cursor, VS Code, and Claude Desktop — or via the hosted playground at arbuilder.app.


2. Deliverables & Milestone Completion

All 5 milestones have been completed and merged to the main branch.

# Milestone Description Status PRs
M1 Proposal + PoC Improvement Updated proposal, improved PoC, documentation Complete
M2 Stylus + SDK RAG Stylus code generation (6 tools), Arbitrum SDK bridging (3 tools), MCP integration, tutorial video Complete #4, #5, #6, #7
M3 Full dApp Builder Backend, frontend, indexer, oracle, orchestration (5 tools), hybrid RAG, ABI extraction Complete #9, #10, #11, #12, #13
M4 Orbit Integration Chain config, rollup deployment, validator setup, Q&A, orchestration (5 tools) Complete #14
M5 Final Report + Metrics ARBuilder v1.0, final report, KPIs Complete #15, #16, #17, #19

Key Technical Deliverables

Component Details
MCP Tools 19 tools across 4 modules (M1: 6, M2: 3, M3: 5, M4: 5)
Templates 7 Stylus contract templates + 9 Orbit deployment templates
RAG Pipeline Hybrid BM25 + vector search (BGE-M3, 1024 dimensions) + cross-encoder reranking
Code Validation Docker-based cargo check with up to 3 auto-fix attempts, 6-phase fix architecture
Hosted Service Cloudflare Workers (Workers AI, Vectorize, D1, KV, Queue)
Test Suite 451 unit/integration tests including TypeScript compilation and bash syntax validation
Ingestion Pipeline Worker-native cron (every 6 hours) — scrape, chunk, embed, upsert

3. Developer Adoption & Usage Metrics

3.1 Platform Usage

Data source: Cloudflare D1 usage_logs (MCP endpoint)

Metric Value
Total code generation requests 1,921
Total LLM tokens consumed 5,340,565
Overall success rate 99.7% (1,915/1,921)
Average latency 15.6 seconds
Peak daily usage 333 requests (March 5, 2026)
Active tracking period Feb 24 – Mar 8, 2026

3.2 Requests by Tool

Tool Requests Category
generate_stylus_code 488 M1: Stylus
generate_bridge_code 327 M2: SDK
generate_messaging_code 183 M2: SDK
ask_bridging 183 M2: SDK
orchestrate_dapp 94 M3: dApp
generate_indexer 84 M3: dApp
generate_tests 69 M1: Stylus
ask_stylus 68 M1: Stylus
generate_frontend 60 M3: dApp
generate_backend 57 M3: dApp
get_workflow 51 M1: Stylus
ask_orbit 44 M4: Orbit
generate_orbit_deployment 42 M4: Orbit
get_stylus_context 38 M1: Stylus
generate_oracle 35 M3: dApp
generate_validator_setup 33 M4: Orbit
generate_orbit_config 33 M4: Orbit
orchestrate_orbit 32 M4: Orbit

3.3 Developer Reach

Channel Details
Registered users (arbuilder.app) 5 accounts with API keys
External developers with mainnet deployments 5 unique developers
GitHub maintainers 4 (wms2537, DiegoFloresWenHao, macoloye, ngjupeng)
GitHub stars 21
YouTube videos 3 tutorials published
Glama quality score AAA (highest tier)

4. Mainnet Deployments — Case Studies

Five projects built with ARBuilder have been independently deployed to Arbitrum One mainnet by external developers:

# Project Developer Contract Address Description
1 Arbitrum TipJar jaysun15 0xba39c706dc01a10c974d5dc355e0725def232e2e On-chain tipping
2 ArbiDrop Jalaa532 0x27ccb5c8da8ae0e2c8b349a0a7d14627429c9569 Token airdrop distribution
3 ArbTokenLaunch benedicther 0x1Da2ce71c789E43775c374920b345998B1F72abC Token launch platform
4 Credential Revocation Registry ajeelll 0x5c31858bd9769cfc29dc36f0cb40bc90cdff321a Verifiable credential registry
5 DisasterReliefLedger samdasak 0xff5a49998772f123c26333fa3a033bdb9cd1fdc7 Disaster relief fund tracking

Testnet projects (Arbitrum Sepolia):

  1. test-erc20-stylus — ERC20 token on Stylus SDK 0.10.0
  2. arcadedao-orbit — Orbit chain deployment
  3. prediction-market-dapp — Full-stack prediction market

5. KPI Achievement

KPI Target Achieved Evidence
Unique developers ≥10 12 Registered users + GitHub contributors + mainnet deployers (deduplicated)
Code generation requests ≥100 1,921 (19.2x target) Cloudflare D1 usage_logs — tracked Feb 24 – Mar 8, 2026 (schema)
GitHub stars ≥20 21 GitHub
Community contributions ≥5 8 issues, 18 merged PRs Issues / PRs
Case studies ≥3 5 See Section 4 — all with on-chain contract addresses
Projects deployed to mainnet ≥5 5 See Section 4 — verified on Arbitrum One

6. Community Engagement & Distribution

6.1 Open Source

Item Details
License MIT
README Comprehensive with architecture, quick start, 19-tool reference
CONTRIBUTING.md Development guide, code style, PR process
Issue templates Bug report + feature request
Good first issues 7 open issues labeled for new contributors

6.2 Directory Listings

Platform Status
Glama Listed — AAA score
awesome-mcp-servers Listed
awesome-stylus PR #26 submitted
mcp.so Issue #788 submitted

6.3 Content & Tutorials

Content Link
Setup & usage walkthrough YouTube
Prediction market dApp demo YouTube
L3 Orbit chain demo YouTube

6.4 Website & SEO

arbuilder.app includes:

  • Landing page with all 4 milestone feature sections
  • Interactive playground with all 19 tools
  • Transparency page (data sources, pipeline status)
  • SEO: JSON-LD structured data, Open Graph, Twitter cards, robots.txt, sitemap.xml
  • LLM discovery endpoint (/llms.txt) for AI search engines

7. Technical Architecture

RAG Pipeline


Query → BM25 + Vector Search (BGE-M3) → RRF Fusion → Cross-Encoder Reranking → LLM Generation

  1. Hybrid search over 40+ curated Arbitrum repos and docs
  2. Cross-encoder reranking for precision
  3. 65 Stylus compilation rules in system prompts
  4. Compile verification via Docker cargo check with 3 auto-fix attempts

Code Quality Pipeline

6-phase fix architecture (Python + TypeScript, kept in sync):

  1. Structural corrections (attributes, extern crate)
  2. Import resolution (alloc, alloy_sol_types)
  3. Storage accessor patterns (getter/setter)
  4. API migration (SDK 0.9.x → 0.10.0)
  5. Type corrections (B256, U256, as_u64)
  6. Output sanitization (garbled LLM output)

Deployment

Mode Stack
Self-hosted Python MCP server via stdio → Cursor / VS Code / Claude Desktop
Hosted Cloudflare Workers, Workers AI, Vectorize, D1, KV, Queue

8. Key Learnings

  1. RAG outperforms fine-tuning for fast-moving SDKs. Stylus SDK went from 0.6 → 0.10.0 in months. RAG allows knowledge base updates in hours, not weeks of retraining.
  2. Compile verification is non-negotiable. The cargo check + auto-fix loop catches errors that static analysis cannot, especially Stylus-specific patterns like self.vm() migration.
  3. Hybrid search matters. BM25 alone misses semantic similarity; vector search alone misses exact API signatures. The combination with cross-encoder reranking significantly improves code quality.
  4. Template + LLM hybrid works best. Templates provide reliable scaffolding (100% success rate); LLM fills in custom logic. This gives consistency for common patterns while maintaining flexibility.
  5. Testing catches real bugs. Our TypeScript compilation tests caught a template substitution ordering bug where CHAIN_ID_PLACEHOLDER was being replaced before PARENT_CHAIN_ID_PLACEHOLDER, corrupting parent chain IDs in generated code.

9. Repository Statistics

Metric Value
Total commits 218
Lines of code (Python + TypeScript) 56,700+
Test cases 451
Pull requests merged 18
Issues created 8 (7 open “good first issue”)
Data sources in knowledge base 40+

10. Future Plans

  • Continue maintaining the knowledge base as Stylus SDK evolves
  • Respond to community issues and contributions via the 7 open “good first issue” items
  • Monitor and update directory listings (awesome-mcp-servers, awesome-stylus, mcp.so)
  • Explore additional Arbitrum ecosystem integrations based on community feedback
  • Track mainnet deployments from new users

ARBuilder is open-source under the MIT license. Built by Quantum3 Labs for the Arbitrum ecosystem.

1 Like

Thank you for the final report @wms2537

You shipped a working open-source tool that generates Stylus, bridging, dApp, and Orbit code. You hit every milestone, posted strong metrics, and helped five independent projects reach mainnet. The focus on real compile checks and up-to-date knowledge is especially valuable. Well done.

From a governance standpoint (grant oversight, accountability, value-for-money, transparency, community impact, and long-term sustainability within the Arbitrum Foundation Developer Tooling program), this is a strong, well-structured final report. It demonstrates clear milestone delivery, measurable outcomes that substantially exceed targets, verifiable on-chain evidence, and responsible open-source practices.

Key Governance Strengths:

Full milestone completion with traceability: All 5 milestones completed and linked to specific PRs. This provides clear auditability of progress against the original grant scope.

KPI over-delivery with evidence: Targets were met or significantly exceeded (e.g., 1,921 code generation requests vs. ≥100; 5 mainnet deployments vs. ≥5; 12 unique developers vs. ≥10). Metrics are backed by concrete sources (Cloudflare D1 logs, GitHub, on-chain addresses).

Transparency & verifiability: Public GitHub repo, hosted service, YouTube tutorials, Glama listing, and five independent mainnet contract addresses allow independent verification.

Open-source hygiene: MIT license, CONTRIBUTING.md, issue templates, good-first-issues, and directory listings show intent to foster community ownership rather than a closed tool.

Technical rigor relevant to ecosystem health: RAG pipeline, compile verification with auto-fix, hybrid search, and SDK version awareness address real pain points (rapid Stylus SDK evolution). This supports broader developer productivity and reduces friction for Arbitrum builders.

Usage quality signals: 99.7% success rate, detailed tool-level breakdown, and external mainnet deployments indicate real utility rather than vanity metrics.

Areas of Constructive Governance Attention:

• Adoption is still early (21 stars, limited registered users).

• Usage data covers only a short window.

• Long-term maintenance plan needs more detail.

Overall: The team delivered useful tooling with clear impact. Good value for the grant.

Opinion:

This grant produced clear results. The over-performance on KPIs and independent mainnet use give solid proof of impact. The technical approach is practical. Continued community growth and maintenance will decide how lasting the tool becomes. At this stage, the delivery looks strong.

Questions:

1. How will you keep the knowledge base updated after the grant ends?

2. Do you have usage or feedback data after mid-March?

3. What plans do you have to grow contributors and users?

4. Can you track downstream impact (e.g., more mainnet deployments or time saved)?

5. Are there ecosystem partners or docs sites where closer integration would help?

6. How easy would it be for others to maintain the project if needed?