---
title: "Abaho Katabarwa (@llmgraph) | Hashnode"
description: "Building LLMGraph — build LLM workflows as a graph, deploy AI assistants in one click. No code. Read the latest articles by Abaho Katabarwa on Hashnode."
url: "https://hashnode.com/@llmgraph"
---

@llmgraph

# Abaho Katabarwa

@llmgraph · Seattle, USA · Joined July 2026

Building LLMGraph — build LLM workflows as a graph, deploy AI assistants in one click. No code.

[Website](https://llmgraph.ai/)

### [Flowise is shutting down: a migration path for your visual LLM workflows](https://llmgraph.hashnode.dev/flowise-is-shutting-down-a-migration-path-for-your-visual-llm-workflows?utm_source=hashnode&utm_medium=feed)

Flowise announced on July 29 that it's winding down. The GitHub repo gets archived on August 10, npm packages and Docker images are being deprecated, and August 31 is end of life. The code stays Apach

2 min read · [llmgraph.hashnode.dev](https://llmgraph.hashnode.dev/flowise-is-shutting-down-a-migration-path-for-your-visual-llm-workflows?utm_source=hashnode&utm_medium=feed)

[Aug 5](https://hashnode.com/posts/flowise-is-shutting-down-a-migration-path-for-your-visual-llm-workflows/6a727e2985d5a35642b1c2f7)

### [Hexagonal architecture in Rust, and why it makes your codebase legible to coding agents](https://llmgraph.hashnode.dev/hexagonal-architecture-in-rust-and-why-it-makes-your-codebase-legible-to-coding-agents?utm_source=hashnode&utm_medium=feed)

Coding agents are good at local edits and bad at holding a whole system in their head. Ask one to fix a function and it does fine. Ask it to "add Postgres support" to a codebase where the database cal

8 min read · [llmgraph.hashnode.dev](https://llmgraph.hashnode.dev/hexagonal-architecture-in-rust-and-why-it-makes-your-codebase-legible-to-coding-agents?utm_source=hashnode&utm_medium=feed)

[Jul 28](https://hashnode.com/posts/hexagonal-architecture-in-rust-and-why-it-makes-your-codebase-legible-to-coding-agents/6a691c34ad4456ec0af4454c)

### [What it actually costs to run a RAG chatbot](https://llmgraph.hashnode.dev/what-it-actually-costs-to-run-a-rag-chatbot?utm_source=hashnode&utm_medium=feed)

"How much will this cost to run?" is the question that kills more AI side projects than any technical problem. People build a working RAG chatbot in a weekend, then freeze because they have no idea wh

5 min read · [llmgraph.hashnode.dev](https://llmgraph.hashnode.dev/what-it-actually-costs-to-run-a-rag-chatbot?utm_source=hashnode&utm_medium=feed)

[Jul 28](https://hashnode.com/posts/what-it-actually-costs-to-run-a-rag-chatbot/6a689be7ec84630faee9312b)

### [Turn a folder of PDFs into a question-answering API in an afternoon](https://llmgraph.hashnode.dev/turn-a-folder-of-pdfs-into-a-question-answering-api-in-an-afternoon?utm_source=hashnode&utm_medium=feed)

Someone hands you 200 PDFs and asks for a "chatbot that knows this stuff." You could read all 200. Or you could build a small API that reads them for you and answers questions with citations. This pos

5 min read · [llmgraph.hashnode.dev](https://llmgraph.hashnode.dev/turn-a-folder-of-pdfs-into-a-question-answering-api-in-an-afternoon?utm_source=hashnode&utm_medium=feed)

[Jul 28](https://hashnode.com/posts/turn-a-folder-of-pdfs-into-a-question-answering-api-in-an-afternoon/6a68299f4792465b6e6a43a0)
