AI is systems engineering
The hardest part of production AI agents is the infrastructure around the models.
The industry races to adopt large language models (LLMs) with unbounded potential. While models get more capable, what makes them work in production is the infrastructure around them.
LLM Works
The next-generation
open-source architecture
for AI agents
Agents
AI agents running in production
llm-news
LiveA live tech news feed, curated and ranked by AI.
Aggregates and ranks tech and AI news from 70+ sources, refreshed hourly. Articles are summarized and rated for relevance; thematic clusters surface evolving stories.
Try news.llm-works.ai →llm-xray
LiveDeep research powered by AI.
Decision-grade research output: calibrated verdicts through self-refining loops, with a plan-as-protagonist architecture that surfaces what was checked, what changed the verdict, and what's still open.
Try xray.llm-works.ai →Platform
An open-source substrate for the engineering layer around production LLM agents
- Five independent modules, each usable on its own.
- Clean on-LLM / off-LLM boundary via verb pattern.
- Response guards enforce contracts on model output.
- Model-agnostic inference across providers.
- Cost transparency and per-call tracking.
- Rails for composable and automated agent loops.
- Clean code, strict typing, ~9k tests, 1:1 test-to-source ratio.
Every agent runs on a modular architecture enabling a clean on-LLM / off-LLM boundary.
The engineering layer around the model turns model calls into production agents. The platform builds it once, so every agent inherits the capabilities.
Platforms that ship as one blob are hard to compose, extend, or swap parts of. Adoption is all-or-nothing and hard to walk back.
Without higher-level abstractions, business logic becomes complex. Every model call turns into request formatting, response parsing, and retry handling.
Every dependency, upgrade, and breaking change costs engineering hours. The maintenance bill grows with the codebase.
Story
AI is going through an engineering shift seen in several industries before