Cedric Clyburn
@cedricclyburn.com
Developer Advocate at Red Hat • Organizer KCD New York • Previously at MongoDB • containers, k8s, & everything in between
Pinned
Cedric Clyburn
@cedricclyburn.com
· May 9
What a time I had at @devoxx.uk this week, the energy was fantastic and it’s an honor to have attended and spoke at #DevoxxUK for the first time! Thanks to the Red Hat team with @kevindubois.com @danieloh30.bsky.social @myfear.com and many other rockstars for making this happen! 🚀 Slides below :)
Reposted by Cedric Clyburn
What can LLMs actually do with messy, domain-heavy data? 🤖📊
@cedricclyburn.com & Andrew Igdal explore how LLMs can help query and explain complex residential energy data, where the models break down, and why humans still need to do the science.
🔗 www.dev2next.com/speaker/67ab...
@cedricclyburn.com & Andrew Igdal explore how LLMs can help query and explain complex residential energy data, where the models break down, and why humans still need to do the science.
🔗 www.dev2next.com/speaker/67ab...
August 28, 2026 at 4:00 PM
What can LLMs actually do with messy, domain-heavy data? 🤖📊
@cedricclyburn.com & Andrew Igdal explore how LLMs can help query and explain complex residential energy data, where the models break down, and why humans still need to do the science.
🔗 www.dev2next.com/speaker/67ab...
@cedricclyburn.com & Andrew Igdal explore how LLMs can help query and explain complex residential energy data, where the models break down, and why humans still need to do the science.
🔗 www.dev2next.com/speaker/67ab...
3 million views on the IBM Technology whiteboard explainers this week 🤯 Still doesn't feel real. Best part is it's free :) for students, engineers, managers, people with no technical background at all, everyone can learn AI and tech in an accessible way. Thanks for watching, and keep learning!
August 5, 2026 at 6:13 PM
3 million views on the IBM Technology whiteboard explainers this week 🤯 Still doesn't feel real. Best part is it's free :) for students, engineers, managers, people with no technical background at all, everyone can learn AI and tech in an accessible way. Thanks for watching, and keep learning!
The energy in SF at #AIWorldFair is electric ⚡️ I want to give a big thanks to the team for having me highlight the open source Docling (docling.ai) project & how to turn unstructured data into AI-ready formats like Markdown/JSON (or straight into LangChain and your agents 🤖)
🎥 youtu.be/-x5GEVnkuRw
🎥 youtu.be/-x5GEVnkuRw
Structuring the Unstructured - Cedric Clyburn, Red Hat
YouTube video by AI Engineer
youtu.be
July 1, 2026 at 8:22 PM
The energy in SF at #AIWorldFair is electric ⚡️ I want to give a big thanks to the team for having me highlight the open source Docling (docling.ai) project & how to turn unstructured data into AI-ready formats like Markdown/JSON (or straight into LangChain and your agents 🤖)
🎥 youtu.be/-x5GEVnkuRw
🎥 youtu.be/-x5GEVnkuRw
You might’ve noticed I love open source and the impact that these projects have on the community 👀
that’s why this past week @devbcn.bsky.social I had the coolest opportunity to join my COUSIN who’s a PhD candidate and show open models + cloud-native for multi agent systems for research :)
that’s why this past week @devbcn.bsky.social I had the coolest opportunity to join my COUSIN who’s a PhD candidate and show open models + cloud-native for multi agent systems for research :)
June 23, 2026 at 9:34 AM
You might’ve noticed I love open source and the impact that these projects have on the community 👀
that’s why this past week @devbcn.bsky.social I had the coolest opportunity to join my COUSIN who’s a PhD candidate and show open models + cloud-native for multi agent systems for research :)
that’s why this past week @devbcn.bsky.social I had the coolest opportunity to join my COUSIN who’s a PhD candidate and show open models + cloud-native for multi agent systems for research :)
This year @devoxx.uk we asked a simple question: can we use local models as AI code assistants? 🤔
The answer? Yes… and no! But you should check out the recording though and see what worked (like MCP, Skills.MD, and more) as well as what to know about local LLMs for devs :)
🎥 youtu.be/Lhqp7gKXu2w
The answer? Yes… and no! But you should check out the recording though and see what worked (like MCP, Skills.MD, and more) as well as what to know about local LLMs for devs :)
🎥 youtu.be/Lhqp7gKXu2w
Local Development in the AI Era by Cedrci Clyburn & Kevin Dubois
YouTube video by Devoxx UK
youtu.be
May 18, 2026 at 5:53 PM
This year @devoxx.uk we asked a simple question: can we use local models as AI code assistants? 🤔
The answer? Yes… and no! But you should check out the recording though and see what worked (like MCP, Skills.MD, and more) as well as what to know about local LLMs for devs :)
🎥 youtu.be/Lhqp7gKXu2w
The answer? Yes… and no! But you should check out the recording though and see what worked (like MCP, Skills.MD, and more) as well as what to know about local LLMs for devs :)
🎥 youtu.be/Lhqp7gKXu2w
Reposted by Cedric Clyburn
@cedricclyburn.com "Shows the 5 Podman Features You Should Know: Kubernetes & Containers Simplified" in this YouTube video: www.youtube.com/watch?v=dEy3.... Can you guess what they are? @opensource #podman
5 Podman Features You Should Know: Kubernetes & Containers Simplified
YouTube video by IBM Technology
www.youtube.com
April 23, 2026 at 5:26 PM
@cedricclyburn.com "Shows the 5 Podman Features You Should Know: Kubernetes & Containers Simplified" in this YouTube video: www.youtube.com/watch?v=dEy3.... Can you guess what they are? @opensource #podman
AI coding tools are about to get more expensive, and the @anthropic.com news yesterday is a good indicator of what’s to come ($20 to $100 for Claude Code). Understandable, because GPU compute isn’t cheap 👀
Running models in-house with #vLLM is starting to look quite nice!
Running models in-house with #vLLM is starting to look quite nice!
April 22, 2026 at 7:03 PM
AI coding tools are about to get more expensive, and the @anthropic.com news yesterday is a good indicator of what’s to come ($20 to $100 for Claude Code). Understandable, because GPU compute isn’t cheap 👀
Running models in-house with #vLLM is starting to look quite nice!
Running models in-house with #vLLM is starting to look quite nice!
Had an AWESOME conversation with the @allthingsopen.bsky.social community about local LLMs on small hardware: model compression can quantize a model from 220 GB → 55 GB with <1% accuracy loss, and inference engines like vLLM help run them fast and efficiently.
🎥 www.youtube.com/watch?v=xGqV...
🎥 www.youtube.com/watch?v=xGqV...
Local LLMs are about to change everything – here's why quantization matters
YouTube video by All Things Open
www.youtube.com
April 17, 2026 at 6:43 PM
Had an AWESOME conversation with the @allthingsopen.bsky.social community about local LLMs on small hardware: model compression can quantize a model from 220 GB → 55 GB with <1% accuracy loss, and inference engines like vLLM help run them fast and efficiently.
🎥 www.youtube.com/watch?v=xGqV...
🎥 www.youtube.com/watch?v=xGqV...
Reposted by Cedric Clyburn
🔌 Messy data meets LLMs!
Join Andy Igdal and Cedric Clyburn (@cedricclyburn.bsky.social) at DevBcn 2026.
Learn how Python and AI can tackle residential electrification data in the Big Data & AI track! 📊🤖
📅 June 16-17
🔗 buff.ly/dz1tICU
#devbcn26
Join Andy Igdal and Cedric Clyburn (@cedricclyburn.bsky.social) at DevBcn 2026.
Learn how Python and AI can tackle residential electrification data in the Big Data & AI track! 📊🤖
📅 June 16-17
🔗 buff.ly/dz1tICU
#devbcn26
April 14, 2026 at 12:01 PM
🔌 Messy data meets LLMs!
Join Andy Igdal and Cedric Clyburn (@cedricclyburn.bsky.social) at DevBcn 2026.
Learn how Python and AI can tackle residential electrification data in the Big Data & AI track! 📊🤖
📅 June 16-17
🔗 buff.ly/dz1tICU
#devbcn26
Join Andy Igdal and Cedric Clyburn (@cedricclyburn.bsky.social) at DevBcn 2026.
Learn how Python and AI can tackle residential electrification data in the Big Data & AI track! 📊🤖
📅 June 16-17
🔗 buff.ly/dz1tICU
#devbcn26
Self-hosting LLM’s typically includes a set of requirements for our infrastructure, ex:
🏎️ Hardware accelerators
⚙️ System & model configuration
📚 Specific libraries/dependencies
That’s why @cern.voxxeddays.ch I was honored to demo Ramalama.ai, a project that containers to safely run AI models 🤖
🏎️ Hardware accelerators
⚙️ System & model configuration
📚 Specific libraries/dependencies
That’s why @cern.voxxeddays.ch I was honored to demo Ramalama.ai, a project that containers to safely run AI models 🤖
April 9, 2026 at 6:24 PM
Self-hosting LLM’s typically includes a set of requirements for our infrastructure, ex:
🏎️ Hardware accelerators
⚙️ System & model configuration
📚 Specific libraries/dependencies
That’s why @cern.voxxeddays.ch I was honored to demo Ramalama.ai, a project that containers to safely run AI models 🤖
🏎️ Hardware accelerators
⚙️ System & model configuration
📚 Specific libraries/dependencies
That’s why @cern.voxxeddays.ch I was honored to demo Ramalama.ai, a project that containers to safely run AI models 🤖
Reposted by Cedric Clyburn
LLM Inference workloads are becoming monolithic, heavy, & hard to scale. That's where platform engineers can embrace llm_d, a new open-source effort that’s starting to tackle a problem we’re seeing more and more in prod ML stacks!!! 🎧 to @cedricclyburn.com & Christopher Nuland👇 to learn more
April 5, 2026 at 1:25 PM
LLM Inference workloads are becoming monolithic, heavy, & hard to scale. That's where platform engineers can embrace llm_d, a new open-source effort that’s starting to tackle a problem we’re seeing more and more in prod ML stacks!!! 🎧 to @cedricclyburn.com & Christopher Nuland👇 to learn more
Live from #KubeCon Europe in Amsterdam! 🇳🇱
Big announcement from the Red Hat booth: llm-d, a cloud-native way to run AI at scale with major performance & cost savings.
+ ran a workshop on RAG at scale using KubeFlow & Docling on Kubernetes. Slides below 👇
Big announcement from the Red Hat booth: llm-d, a cloud-native way to run AI at scale with major performance & cost savings.
+ ran a workshop on RAG at scale using KubeFlow & Docling on Kubernetes. Slides below 👇
March 25, 2026 at 3:23 PM
Live from #KubeCon Europe in Amsterdam! 🇳🇱
Big announcement from the Red Hat booth: llm-d, a cloud-native way to run AI at scale with major performance & cost savings.
+ ran a workshop on RAG at scale using KubeFlow & Docling on Kubernetes. Slides below 👇
Big announcement from the Red Hat booth: llm-d, a cloud-native way to run AI at scale with major performance & cost savings.
+ ran a workshop on RAG at scale using KubeFlow & Docling on Kubernetes. Slides below 👇
If you’ve seen my “silly slide” of all the open-source AI projects at past dev conferences, this week at #KubeCon we’re putting them together! Join me & friends for a hands-on workshop: build a sovereign RAG app on K8s with Kubeflow, Knative, Docling & vLLM. Wed 3/25 @ 11am 🚀
🔗 sched.co/2CW1f
🔗 sched.co/2CW1f
March 23, 2026 at 9:49 PM
If you’ve seen my “silly slide” of all the open-source AI projects at past dev conferences, this week at #KubeCon we’re putting them together! Join me & friends for a hands-on workshop: build a sovereign RAG app on K8s with Kubeflow, Knative, Docling & vLLM. Wed 3/25 @ 11am 🚀
🔗 sched.co/2CW1f
🔗 sched.co/2CW1f
Many folks compare whether “Opus 4.6 is better than ChatGPT 5.4” but there’s quietly been TONS of progress in the open source world of AI too (ex. #DeepSeek, #Llama) 🤖 with no rate limits, ads, and 100% local!
📰 Check out the article on @allthingsopen.bsky.social: allthingsopen.org/articles/run...
📰 Check out the article on @allthingsopen.bsky.social: allthingsopen.org/articles/run...
Everything you need to know about running LLMs locally | We Love Open Source • All Things Open
Learn how to run open source LLMs locally using Ollama, vLLM, and other tools. Discover model selection strategies, deployment options, and how to save costs while maintaining complete privacy and con...
allthingsopen.org
March 9, 2026 at 4:11 PM
Many folks compare whether “Opus 4.6 is better than ChatGPT 5.4” but there’s quietly been TONS of progress in the open source world of AI too (ex. #DeepSeek, #Llama) 🤖 with no rate limits, ads, and 100% local!
📰 Check out the article on @allthingsopen.bsky.social: allthingsopen.org/articles/run...
📰 Check out the article on @allthingsopen.bsky.social: allthingsopen.org/articles/run...
What does it look like to integrate #MCP into real enterprise workflows? This week at @devnexus.bsky.social we showed how to run, inspect, and scale agentic AI for debugging a Kubernetes clusters, diagnosing Ansible jobs, and much more!
Check out the slides below ⬇️ as well as the MCP servers used!
Check out the slides below ⬇️ as well as the MCP servers used!
March 6, 2026 at 6:00 PM
What does it look like to integrate #MCP into real enterprise workflows? This week at @devnexus.bsky.social we showed how to run, inspect, and scale agentic AI for debugging a Kubernetes clusters, diagnosing Ansible jobs, and much more!
Check out the slides below ⬇️ as well as the MCP servers used!
Check out the slides below ⬇️ as well as the MCP servers used!
Reposted by Cedric Clyburn
Dev track is deploying heavy artillery.
Stop polyfilling frontend and duct-taping backend. Time to build stacks that scale.
The engineers: Switch Angel, @tej.as, @abtris.bsky.social, Krasimir Tsonev, @clytaemnestra.bsky.social, @utilitybend.com, @cedricclyburn.com, @ericwbailey.website & more.
Stop polyfilling frontend and duct-taping backend. Time to build stacks that scale.
The engineers: Switch Angel, @tej.as, @abtris.bsky.social, Krasimir Tsonev, @clytaemnestra.bsky.social, @utilitybend.com, @cedricclyburn.com, @ericwbailey.website & more.
March 3, 2026 at 7:26 AM
Dev track is deploying heavy artillery.
Stop polyfilling frontend and duct-taping backend. Time to build stacks that scale.
The engineers: Switch Angel, @tej.as, @abtris.bsky.social, Krasimir Tsonev, @clytaemnestra.bsky.social, @utilitybend.com, @cedricclyburn.com, @ericwbailey.website & more.
Stop polyfilling frontend and duct-taping backend. Time to build stacks that scale.
The engineers: Switch Angel, @tej.as, @abtris.bsky.social, Krasimir Tsonev, @clytaemnestra.bsky.social, @utilitybend.com, @cedricclyburn.com, @ericwbailey.website & more.
With agentic coding tools like #ClaudeCode, #Cursor, and #Codex, how can you get the results you need from an LLM without spending all your time going back and forth about a wrong dependency or missing test cases 😆 well…
🎥 Spec-Driven Development: AI Assisted Coding Explained: youtu.be/mViFYTwWvcM
🎥 Spec-Driven Development: AI Assisted Coding Explained: youtu.be/mViFYTwWvcM
Spec-Driven Development: AI Assisted Coding Explained
YouTube video by IBM Technology
youtu.be
March 2, 2026 at 8:50 PM
With agentic coding tools like #ClaudeCode, #Cursor, and #Codex, how can you get the results you need from an LLM without spending all your time going back and forth about a wrong dependency or missing test cases 😆 well…
🎥 Spec-Driven Development: AI Assisted Coding Explained: youtu.be/mViFYTwWvcM
🎥 Spec-Driven Development: AI Assisted Coding Explained: youtu.be/mViFYTwWvcM
🤖 AI Agents are awesome… until they aren’t!
What just happened with an 🦞 OpenClaw (ClawdBot/MoltBot) agent in the Matplotlib project on GitHub shows the potential challenges with giving AI Agents (LLM + Tools + Reasoning) the ability to act autonomously. It’s why guardrails and auth are important!
What just happened with an 🦞 OpenClaw (ClawdBot/MoltBot) agent in the Matplotlib project on GitHub shows the potential challenges with giving AI Agents (LLM + Tools + Reasoning) the ability to act autonomously. It’s why guardrails and auth are important!
February 23, 2026 at 11:42 PM
🤖 AI Agents are awesome… until they aren’t!
What just happened with an 🦞 OpenClaw (ClawdBot/MoltBot) agent in the Matplotlib project on GitHub shows the potential challenges with giving AI Agents (LLM + Tools + Reasoning) the ability to act autonomously. It’s why guardrails and auth are important!
What just happened with an 🦞 OpenClaw (ClawdBot/MoltBot) agent in the Matplotlib project on GitHub shows the potential challenges with giving AI Agents (LLM + Tools + Reasoning) the ability to act autonomously. It’s why guardrails and auth are important!
Reposted by Cedric Clyburn
Want to build fast? We’ve got the blueprints.
🔹 @lomagnette.bsky.social: Building Interoperable AI Agents in 30 mins.
🔹 @danieloh30.bsky.social, @cedricclyburn.com & Legare Kerrison: A crash course in Open Source AI.
🔹 @marianne-h.bsky.social: Unveiling the math behind it all.
🔹 @lomagnette.bsky.social: Building Interoperable AI Agents in 30 mins.
🔹 @danieloh30.bsky.social, @cedricclyburn.com & Legare Kerrison: A crash course in Open Source AI.
🔹 @marianne-h.bsky.social: Unveiling the math behind it all.
February 23, 2026 at 12:01 PM
Want to build fast? We’ve got the blueprints.
🔹 @lomagnette.bsky.social: Building Interoperable AI Agents in 30 mins.
🔹 @danieloh30.bsky.social, @cedricclyburn.com & Legare Kerrison: A crash course in Open Source AI.
🔹 @marianne-h.bsky.social: Unveiling the math behind it all.
🔹 @lomagnette.bsky.social: Building Interoperable AI Agents in 30 mins.
🔹 @danieloh30.bsky.social, @cedricclyburn.com & Legare Kerrison: A crash course in Open Source AI.
🔹 @marianne-h.bsky.social: Unveiling the math behind it all.
Reposted by Cedric Clyburn
AI sits to your right, but you're the captain
- @vilojona.bsky.social: Practical ways to keep AI codegen under control
- @vjovanov.bsky.social: Taming GraalVM with AI
- @timtebeek.github.io: Deterministic modernization in the AI age
- @kevindubois.com @cedricclyburn.com: Local development strategies
- @vilojona.bsky.social: Practical ways to keep AI codegen under control
- @vjovanov.bsky.social: Taming GraalVM with AI
- @timtebeek.github.io: Deterministic modernization in the AI age
- @kevindubois.com @cedricclyburn.com: Local development strategies
February 16, 2026 at 9:29 AM
AI sits to your right, but you're the captain
- @vilojona.bsky.social: Practical ways to keep AI codegen under control
- @vjovanov.bsky.social: Taming GraalVM with AI
- @timtebeek.github.io: Deterministic modernization in the AI age
- @kevindubois.com @cedricclyburn.com: Local development strategies
- @vilojona.bsky.social: Practical ways to keep AI codegen under control
- @vjovanov.bsky.social: Taming GraalVM with AI
- @timtebeek.github.io: Deterministic modernization in the AI age
- @kevindubois.com @cedricclyburn.com: Local development strategies
Today kicks off @jfokus.se in Stockholm 🇸🇪 and we just delivered our workshop on building with open source AI models using:
⚡️ #vLLM serve local LLM’s as a local API endpoint
🦜 @langchain4j.dev for adding LLM capabilities in our Java application
Was a huge hit! Slides ⬇️
⚡️ #vLLM serve local LLM’s as a local API endpoint
🦜 @langchain4j.dev for adding LLM capabilities in our Java application
Was a huge hit! Slides ⬇️
February 2, 2026 at 4:16 PM
Today kicks off @jfokus.se in Stockholm 🇸🇪 and we just delivered our workshop on building with open source AI models using:
⚡️ #vLLM serve local LLM’s as a local API endpoint
🦜 @langchain4j.dev for adding LLM capabilities in our Java application
Was a huge hit! Slides ⬇️
⚡️ #vLLM serve local LLM’s as a local API endpoint
🦜 @langchain4j.dev for adding LLM capabilities in our Java application
Was a huge hit! Slides ⬇️
Reposted by Cedric Clyburn
Automatizar tu vida con servidores MCP: integraciones, flujos y cómo conectar herramientas para que trabajen por ti ⚙️ Con @cedricclyburn.com en T3chFest 2026
How I automated my life with MCP Servers - T3chFest 2026
Being a developer these days means you’re not only writing code, but also a Linux admin, a DevOps en...
t3chfest.es
January 29, 2026 at 5:07 PM
Automatizar tu vida con servidores MCP: integraciones, flujos y cómo conectar herramientas para que trabajen por ti ⚙️ Con @cedricclyburn.com en T3chFest 2026
I’m excited to bring #Ramalama, the container-native project to run AI models locally, to @cern.voxxeddays.ch 🙌
We’ll show how fast devs can spin up an open source model using their favorite container engine (shoutout @podmanio.bsky.social) for RAG (Q&A on PDF’s) and Agentic (calling API’s) 🤖
We’ll show how fast devs can spin up an open source model using their favorite container engine (shoutout @podmanio.bsky.social) for RAG (Q&A on PDF’s) and Agentic (calling API’s) 🤖
January 23, 2026 at 7:44 PM
I’m excited to bring #Ramalama, the container-native project to run AI models locally, to @cern.voxxeddays.ch 🙌
We’ll show how fast devs can spin up an open source model using their favorite container engine (shoutout @podmanio.bsky.social) for RAG (Q&A on PDF’s) and Agentic (calling API’s) 🤖
We’ll show how fast devs can spin up an open source model using their favorite container engine (shoutout @podmanio.bsky.social) for RAG (Q&A on PDF’s) and Agentic (calling API’s) 🤖
@jfokus.se is BACK for its 20th year and I’m so happy to be hosting a workshop on open source models & how to scale them up on #Kubernetes! We’ll feature projects including #vLLM + @langchain4j.dev + @promptfoo.bsky.social and more for enterprise AI deployment, app dev, and testing 🔥
January 12, 2026 at 4:32 PM
@jfokus.se is BACK for its 20th year and I’m so happy to be hosting a workshop on open source models & how to scale them up on #Kubernetes! We’ll feature projects including #vLLM + @langchain4j.dev + @promptfoo.bsky.social and more for enterprise AI deployment, app dev, and testing 🔥
Really excited to share that our team at Red Hat is HIRING! 🎉
We're looking for excited new graduates with a passion for open source AI, interested in creating content to help developers, and traveling to meetups/conferences!
🔗 AI Developer Advocate: redhat.wd5.myworkdayjobs.com/Jobs/job/Bos...
We're looking for excited new graduates with a passion for open source AI, interested in creating content to help developers, and traveling to meetups/conferences!
🔗 AI Developer Advocate: redhat.wd5.myworkdayjobs.com/Jobs/job/Bos...
AI Developer Advocate
About the Job At Red Hat, we believe the future of AI is open source. The Red Hat Artificial Intelligence Business Unit (AI BU) is seeking to hire a Developer Advocate to help grow awareness of Red Ha...
redhat.wd5.myworkdayjobs.com
December 20, 2025 at 3:58 AM
Really excited to share that our team at Red Hat is HIRING! 🎉
We're looking for excited new graduates with a passion for open source AI, interested in creating content to help developers, and traveling to meetups/conferences!
🔗 AI Developer Advocate: redhat.wd5.myworkdayjobs.com/Jobs/job/Bos...
We're looking for excited new graduates with a passion for open source AI, interested in creating content to help developers, and traveling to meetups/conferences!
🔗 AI Developer Advocate: redhat.wd5.myworkdayjobs.com/Jobs/job/Bos...