CrewAI plus open-source LLMs for marketing strategy

David Pickett

09 Jan 2026

People: Me

Idea: Tested whether local/open-source models can handle real marketing strategy work using CrewAI as the orchestration layer.

Details:

Wanted to see how open source tools do for automating some tasks in marketing
Used gpt-oss-120b as the backbone model
Ran everything through CrewAI for agent orchestration
Got Joe's input on a sample prompt tied to the Koʻaka launch
First agent handled web search tasks for market research
Then additional passes/agents did marketing strategist planning, review, content outlining, and a sample set of post contents
System generated an actual strategy document
Also spit out a set of sample social post content
The whole pipeline ran on open LLMs which is pretty cool for data sovereignty
Proof of concept worked—now curious how it holds up at scale

Read more

Neural Network Intent Routing with UIUC's LLMRouter

People: David Idea: Tested UIUC's LLMRouter framework as an alternative to LiteLLM's semantic routing—this one trains an actual neural network for intent classification and can run on hardware as small as a Raspberry Pi with 4GB of ram. Details: * Wanted to compare this against last

Basic Semantic Routing with LiteLLM Proxy

People: David Idea: Testing semantic routing as a way to automatically send LLM requests to different models based on what the user is asking—part of a bigger vision for smart edge-to-hub-to-cloud routing on our Maui cluster. Details: * Our LiteLLM proxy already bundles multiple machines into one API endpoint, so

Automous terminal agent accessible through Slack

People: David Idea: Testing KIRA, Krafton's open-source project that lets you run a full Claude Code instance through Slack, on our local PMF hardware. Details: * Nicole mentioned wanting more Slack bot and automation options for the team * Found Krafton's KIRA project on GitHub which does exactly

Qwen3-32B on AMD's 7900XTX

People: Me Idea: I wanted to see how well the Qwen3-32B model runs on an AMD 7900XTX using different quantization formats and inference backends—spoiler: AWQ is not the move on this generation of consumer AMD card. Details: * Tested on a host system with Ubuntu 24.04 with ROCm 7.