top | item 47118498

Show HN: AI-Native Architecture Series (Open-Source)

3 points| madawei2699 | 1 month ago |github.com | reply

Hi HN,

Open-sourced my complete AI-native architecture series from a solo builder project (spare time).

4 articles (EN/ZH) covering: - Constrained DSL for reliable LLM decisions - 60/40 → 90/10 AI-driven development workflow - "Boring" hybrid agent architecture - Low-cost multi-vendor cloud scaling

Real scale: 28 repos, 538k LOC, 3k+ users, low four-digit RMB yearly infra.

Repo: https://github.com/myinvestpilot/ai-architecture

Pure sharing, no promo. Feedback, critiques, or your solo AI-native experiences welcome!

Thanks

3 comments

[+] JB_5000|1 month ago|reply

actually respect this.

feels like more solo builders are realising agents arent about intelligence, they’re about constraints — DSLs, deterministic layers, boring hybrid architectures.

you stop writing code and start designing guardrails. curious how this scales though.

[+] madawei2699|1 month ago|reply

Thanks JB_5000 — really appreciate you putting it that way. You're spot on: the whole point is constraints over intelligence. Guardrails (DSL, schema, deterministic replay, boring hybrid) are what actually make it production-usable.

On scaling: so far it's handling ~3k trial users + growing paid base with low four-digit RMB yearly infra (queue-driven scale-to-zero, Redis cache, R2 for artifacts). The real bottleneck is still alignment quality (good artifacts + human gates), not the constraint overhead itself. Haven't hit hard walls yet, but I'm sure 10x–100x load will expose new ones.

How about you? Have you seen constrained agents / deterministic layers scale well (or break) at larger sizes? Any guardrails that worked surprisingly well for you?