We are seeing a rise in AI agents in 2025.
Building your own agent can be complex, and all the concepts, frameworks, and practices you need to fol...
For further actions, you may consider blocking this person and/or reporting abuse
This is a really great guide.
Thank you for creating it.
Thanks for reading Divya! Appreciate your support :)
While I do think that this is a decent introduction, I do worry that this is also a whole lot of new surface area to secure. Folks probably shouldn't be using this approach in systems with sensitive data, or mission-critical workloads.
While making the agent may be straightforward, recovering from the breaches the agent will facilitate likely won't be.
Hi Mike, I'm with the CopilotKit team. Would you mind clarifying?
I just wanted to emphasize that sensitive data can be secured by staying on-prem via self hosting, including an LLM that can also be run on your own server.
Having AI tools have access to perform actions and access sensitive systems can lead to threat actors targeting the LLM component to attack your other systems.
No matter how much you secure your onprem systems, the LLM is still a net-new vector.
I appreciate you bringing this up because I'm a strong advocate for security.
To your point, my philosophy is that all systems should be locked down, stress tested, and scanned for vulnerabilities to avoid a threat actor penetrating any system.
I’m glad that this is your philosophy, but as of yet the degree of rigor involved in LLM agents is not great. If an LLM can hallucinate when I’m chatting with it, that’s unpredictable behavior. As a hacker myself, I love unpredictable behavior.
It’s only a matter of time before a massive pile of zero-days emerges from this trend of LLM agents. I doubt it’s far off into the future, and I doubt very seriously if there’s much anybody can do to mitigate that risk while using an LLM agent other than to limit it to tasks that have no access to sensitive information or critical infrastructure or workloads.
Great tutorial for setting up co-agents
Awesome Om! 🔥 I guess the title should include CoAgents haha, totally get that.
Hi Omelet 👋
Really well written article. Will replicate today morning!
Awesome! Let me know if you run into any problems. I've tried to cover everything, so you probably won't get stuck.
Nice Anmol. Been waiting to have an article of this type for awhile!
Awesome Uli. 🔥 I'm sure this will be super helpful for those starting from scratch.
Really great
Well-written and informative article, Anmol.
Thanks for reading, Bonnie. Appreciate it.
👏
When will CopilotKit support CrewAI already?????????
want to be an early tester? 👀
Hi Anmol/Devs,
liked your article, it’s Informative and very well explained. A lot to learn from you.
I have created an ai-agent using fetch.ai uagent. If you get a chance take a look and let us know your thoughts.
Read More
Thanks,
Ram
I took a look at the docs and I only see LangGraph. Are you going to expand support to Haystack, AutoGen, CrewAI or others?
Hi Steven, thanks for checking out the docs!
The short answer is yes we are currently working on expanding to other frameworks on our short term roadmap and we will have some big announcements coming very soon!
Really good informative article really liked the approach simple & easy, yet keeping all details
Thanks for reading, Yash! 🔥 Means a lot.
Thanks for the insightful article Anmol on how to get started with agents! 🚀
Thanks for reading, Nathan! 🙌
Great tutorial
Thanks for checking this out, Abid! 🔥 Let me know if you run into any problems :)
Nice article. Thanks for sharing. We have a similar use case in KaibanJS 👉🏻 kaibanjs.com/
Awesome! Thank you for sharing. I believe someone shared this in my community a few days ago.
I gave it a star on GitHub as well, it's very close to 1k stars! The link isn’t working so I recommend fixing it in case someone else wants to check it out.
Great one, Anmol! 🙌
Thanks for checking this out, Shrijal! 🔥 Time to build something amazing :)
Really cool!
Very interesting and well explained, thank you!
snaptube vidmate
Excellent tutorial on developing AI agents! This step-by-step process makes it simple for newbies to grasp the fundamental concepts and get started immediately. AI agents are playing a more significant role in automating processes and improving decision-making processes. For those who want to scale their solutions, using AI development services can optimize and deploy smart agents effectively. Looking forward to seeing more tutorials like this!"
I've been using agents for several months now as an internal tool and I wish I would've had this guide as a starter to give me a quickstart. It's been a whirlwind to figure out how to build a frontend that shows what the agent is doing on the backend. I'll check out CopilotKit for sure because this may save me a ton of engineering hours.
No worries if you don't know Python, with Spring AI you don't need to spring.io/projects/spring-ai and it is open source WHOO OOOOO
Great post. Thanks 🙏
nice nice nice!
Thank you for sharing
This is really an awesome information, thank you so much Anmol, you are doing a great job sharing such knowledge. Learning a lot from you.
The amount of options to build agent flows are astounding. How is CoPilotKit better/different?
Nice one Anmol, really enjoyed it 🚀
Well articulated. Thanks for making it easy to understand.
Hi,Can you please guide me on this question?
"How can I run deepseek on Ollama?
In a Jupyter environment in Visual Studio Code."
ผู้ร่วมงานผู้บริหารผู้สนับสนุน
Good post!
Very good!
Good job Anmol ... Indeed an informative piece, nicely compiled and written!!
Cool beans!
I found this guide extremely easy to understand.
Thank you!
Awesome information