AI agent tools for architecture
Short answer: Our top pick for architecture: editor, with the highest AgentPick Score (85/100) among tools tagged "architecture". Runners-up: drawio-skill (79) and fallow (78). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | editor | Open-source 3D architectural editor with a local CLI, MCP tools, and practical workflows for humans and AI agents. | 85/100 | ★ 25k | MIT | 14 Oct 2026 |
| #2 | drawio-skill | Agent skill that turns natural language, code, Terraform/K8s, SQL, OpenAPI, AsyncAPI, Protobuf and GraphQL sources into editable, tested draw.io archi… | 79/100 | ★ 10k | MIT | 11 Oct 2026 |
| #3 | fallow | Codebase intelligence for TypeScript and JavaScript. Health, complexity hotspots, duplication, architecture boundaries, circular dependencies, design-… | 78/100 | ★ 5.1k | MIT | 14 Oct 2026 |
| #4 | bionic-gpt | Bionic is sovereign Agentic AI for the enterprise — Runs on-premise and can securely work with your sensitive data and systems. | 68/100 | ★ 2.4k | Apache-2.0 | 7 Oct 2026 |
| #5 | kratos | Your ultimate Go microservices framework for the cloud-native era. | 66/100 | ★ 26k | MIT | 16 Sept 2026 |
| #6 | ArchUnitPython | ArchUnitPython is an architecture testing library. Specify and ensure architecture rules in your Python app. Easy setup and pipeline integration. | 61/100 | ★ 664 | MIT | 6 Oct 2026 |
| #7 | bank-api | The Bank API is a design reference project suitable to bootstrap development for a compliant and modern API. | 43/100 | ★ 844 | See repo | 14 Oct 2026 |
| #8 | sentrux | Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust. | 33/100 | ★ 3.3k | MIT | 19 Mar 2026 |
| #9 | oh-my-mermaid | Turn complex codebases into clear, navigable architecture diagrams with Claude Code. | 30/100 | ★ 3.1k | MIT | 7 Apr 2026 |
| #10 | claude-reviews-claude | Claude reads its own source code — 17-chapter architectural deep-dive into Claude Code v2.1.88. EN/ZH bilingual. | 27/100 | ★ 1.6k | MIT | 1 Apr 2026 |
Source: each project's public GitHub repository (description, stars, license, last push). Listed tools aren't tested or ranked by AgentPick.
How to choose
- Grant the narrowest permissions the server allows.
- Check whether it runs locally or calls a remote service.
- Prefer servers listed in the official MCP registry.
Get the best new agent tools every week. Free, with a verdict on each. Get the weekly digest
Related
AI agent tools for local-first setups →
MCP servers
AI agent tools for knowledge graphs and bases →
MCP servers
AI agent tools for RAG (retrieval-augmented generation) →
MCP servers
AI agent tools for MCP client →
MCP servers
AI agent tools for cybersecurity →
MCP servers
AI agent tools for DevOps →
MCP servers
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.