Solarch  

Bridging diagrams and code via a strict rules engine to stop AI errors.

Your entire workspace, on one canvas. | AI that ships. No more hallucinations.

▶   Try it live — no install — at app.solarch.dev   ·   Learn more at solarch.dev

Why Solarch?   •   Gallery   •   Features   •   Philosophy   •   Self-Hosting   •   Get Involved

---

✦ Why Solarch?

Most AI tools generate code and hope the architecture catches up. Solarch flips that.

It generates architecture first — grounded in a library of canonical patterns, validated by a strict Rules Engine, refined through a self-correcting loop. The AI proposes; the rules verify; only correct graphs ever land on the canvas.

• One canvas for the whole system: 21 node families — controllers, services, repositories, tables, DTOs, queues — and the 16 semantic edges between them.
• AI Architect grounded in GraphRAG: an agentic LLM pipeline pulls from a vector-indexed pattern library. It never starts from a blank context, never invents an API surface.
• Rules Engine that refuses to lie: 32 whitelist rules, 7 anti-patterns, 3 conditional checks. Frontends can't talk to tables. Controllers can't reach repositories. Period.
• Self-correcting loop: Rules rejection feeds back into the agent; the AI revises and tries again until the graph is clean — or never commits.
• Live Instruct Mode: Switch modes and chat with your design. Every answer cites the exact nodes; chips focus the canvas in real time.
• Single-home + reference tabs: Each node lives in one tab. Other tabs import it as a reference, not a copy. One source of truth, multiple views.
• Type-safe from DB to button: Zod schemas at the backend, OpenAPI in the middle, openapi-fetch on the frontend. The API contract is a compile-time check.

---

✦ Gallery

1. Start with a prompt Type what you want to build. The AI Architect kicks in: pulls canonical patterns, plans the graph, and applies it through the Rules Engine.	2. Sketch → architecture (preview) Freeform sketch becomes a structured graph on Refine. Native sketch surface on the roadmap; the AI-driven refine path runs today.
3. Watch it build itself Nodes pop in with zen animations, edges flow with the right semantics — every relationship rule-validated before it commits.	4. Pattern library (preview) A standalone constructor library is on the roadmap. The same canonical patterns already power GraphRAG behind the scenes today.
5. Connect anything — legally Hover a port, drag, snap. The Rules Engine rejects illegal connections instantly. Semantic edges carry meaning, not generic arrows.	6. Every node, purpose-built editor Double-click any node. Column grids for tables, method tables for services, endpoint rows for controllers — no generic JSON forms.

Ask your architecture anything
Switch to Instruct mode and chat with your design. Every citation is a live chip that focuses the canvas with a soft halo.

---

✦ Features

AI & Rules AI Architect: agentic LLM loop with atomic tool calling Rules Engine: 32 whitelist · 7 blacklist (ERR_001..007) · 3 conditional GraphRAG: vector search over a canonical pattern library Self-correction loop: rejection feeds back into agent state, AI revises Vector-native Neo4j: embeddings + graph in one DB, no extra Pinecone Local embeddings: compact multilingual sentence-transformer, on-box, 384-d 21 node families: Table, DTO, Model, Service, Worker, Controller, Repository, Cache, Middleware, and more 16 semantic edges: CALLS, QUERIES, WRITES, PUBLISHES, SUBSCRIBES, THROWS...

Workspace & UI Custom Canvas 2D: 60fps, dual-canvas, viewport culling, devicePixelRatio AI Omni-Bar: Agent (build) + Instruct (Q&A) modes, SSE streaming Live node chips: citations focus the canvas with a soft halo Purpose-built inspectors: per-type editors (4 today, the rest on roadmap) Multi-tab workspace: single-home model + cross-tab references, not copies Edge bundling & routing: obstacle-aware bezier and elbow paths Type-safe API client: Zod → OpenAPI → openapi-fetch + openapi-typescript Light Blueprint design: warm paper, semantic family colors, hairline grid, Satoshi + JetBrains Mono

---

✦ The Philosophy

Solarch doesn't fight AI hallucination — it makes hallucination structurally impossible.

The industry has spent two years asking LLMs to write code. The result: confident hallucinations, ghost APIs, codebases that compile but lie. Hallucination isn't a tuning problem — it's a category error.

Architecture is the level where structure is provable. A controller calls a service. A service queries a repository. A repository writes a table. These relationships are either present or not. They can't be hallucinated.

Solarch stacks three layers that, together, leave no room for an AI to invent something that doesn't exist:

1. GraphRAG. The agent starts every request by retrieving canonical patterns from a vector-indexed library. No blank context, no improvisation from zero.
2. Rules Engine. Every mutation passes a deterministic gate — 32 whitelist rules, 7 anti-patterns, 3 conditional checks. Illegal edges never land. The schema can't be coerced.
3. Self-correction loop. When the Rules Engine rejects a draft, the violation message feeds back into the agent state. The AI revises until the graph is clean, or the request terminates without a commit.

The output isn't trustworthy code. It's provably correct structure.

Provable structure. Targeted intelligence. Zero hallucinated APIs.

---

✦ Self-Hosting

The fastest way to use Solarch is the hosted app — app.solarch.dev — no setup, always up to date.

A unified, one-command self-host (the whole stack — backend, canvas, and a vector-native Neo4j — behind a single docker compose up) is coming soon to this repository. Watch / star to follow along.

# Coming soon
git clone https://github.com/solarch-dev/solarch.git
cd solarch
docker compose up
# → http://localhost:3000

Solarch's stack — NestJS + Zod + Neo4j backend, a custom Canvas 2D frontend, an agentic LLM layer, and local embeddings — will ship here as a single plug-and-play bundle.

---

✦ Get Involved

We welcome feedback, discussions, and contributions.

• 💬 GitHub Discussions — Feature requests, design feedback, questions.
• 🐛 Issues — Bug reports, regressions.
• 🛠️ Contributing Guide — Local setup, conventions, commit style.

✦ License

PolyForm Noncommercial License 1.0.0 — © 2026 Ugur Akdogan.

Free for personal use, research, education, and non-profit organizations. Source is open: fork, learn, modify, share — go for it.
Commercial use requires a separate license — reach out at info@solidea.tech.

See. Understand. Plan.
In one shot.


Solarch.