Profile avatar
ankurkumar.bsky.social
📝 A Techie, Blogger, Educator & Mentor 🖥️ Shares Learnings on Cloud, GenAI, Platform Engineering, Microservices, DevOps, Data Engineering 💙 Loved Husband, Proud Dad 💡 Founder Vedcraft.com - a platform for enabling Cloud, GenAI 🎯 Sports🏎️ 🎾 🏏🏒, Loves ☕🎦📘
75 posts 228 followers 1,011 following
Regular Contributor
Active Commenter
Posts 26 Comments 24

Tried my best to capture most of the #agentic frameworks for building #GenAI apps - let me know if anything missing 👇 medium.com/vedcraft/bui...

submitted 30 days ago • 0 comments

DeepSeek is not just a ChatGPT competition but also a great news for the Open source community as it is the first high quality “reasoning” Open model available for fine-tuning, and self-hosting. Here is the compiled list of Open models for reference 👇 #opensource #LLMs medium.com/vedcraft/top...

submitted 38 days ago • 0 comments

Agentic AI has emerged as one of the most promising GenAI building blocks in 2025, and numerous frameworks have emerged to build agentic apps. Published this article summarizing the key agentic frameworks with their architecture, features, pros/cons👇 medium.com/vedcraft/bui... #GenAI #AgenticAI

submitted 45 days ago • 0 comments

Published a comprehensive list of Agentic frameworks, accompanied by their respective advantages and disadvantages. I have had the privilege of experimenting with several of these frameworks and currently utilize some of them. Please share your experience. medium.com/vedcraft/bui... #GenAI

submitted 47 days ago • 0 comments

Building AI agents for common Cloud operations accelerating organizational’s productivity and efficiency 👇 arxiv.org/html/2407.12...

submitted 58 days ago • 0 comments

From large context window, multi-modal capabilities, accuracy, fine-tuning capabilities, prompt caching, and more - 2025 trends indicate consolidation and maturity of foundation models towards token generation efficiency, lower response time, and decreasing cost👇 blog.dataiku.com/a-dizzying-y...

submitted 61 days ago • 0 comments

From current Agentic AI towards Physical AI (imagine AI-driven robots for physical & immersive work efficiency), Jensen’s CES 25 keynote elevated the LLM to the future of World Foundation Model empowering Robotics along with 🧵

submitted 63 days ago • 4 comments

Top Data Engineering Open Source Apache Tech to Watch for in 2025 👇 1️⃣ Apache Iceberg (Common Open Format) 2️⃣ Apache Atlas (Universal Metadata Management) 3️⃣ Apache Druid (Real-time Analytics DB) 4️⃣ Apache Pinot (Distributed DB) 5️⃣ Apache Hudi (Distributed Data Lake) 6️⃣ Apache Drill (Query Engine)

submitted 72 days ago • 1 comment

Agentic Frameworks on rise and will continue to see more in 2025 (mostly Python)👇 1️⃣ Microsoft AutoGen 2️⃣ LangGraph / LangChain 3️⃣ AutoGPT 4️⃣ CrewAI 5️⃣ Swarm by OpenAI 6️⃣ MetaGPT 7️⃣ Flowise 8️⃣ OpenAGI 9️⃣ HF Transformers Agents 🔟 Camel Others: Langflow, LLMStack Are you aware of any more? #GenAI #Python

submitted 73 days ago • 0 comments

X/Twitter is getting bombarded with hate messages particularly related to immigrants- what happened to the US spirit of welcoming everyone here 🤔

submitted 73 days ago • 0 comments

CRN Top #Kubernetes Startups 👇 1️⃣ AccuKnox (Security Platform) 2️⃣ Cast AI (Cost Automation) 3️⃣ Edgeless Systems (Confidential Computing) 4️⃣ Kubo Labs (Troubleshooting) 5️⃣ RapidFort 6️⃣ Namla (Orchestration) 7️⃣ ScaleOps (Optimisation) 8️⃣ StackBlitz (Browser Env) 9️⃣ Syself 🔟 Zesty www.crn.com/news/cloud/2...

submitted 77 days ago • 0 comments

That’s very well articulated article on Small Language Models along with: 1️⃣ Compression methods: Pruning, Quantization, Low-rank factorization, Knowledge distillation 2️⃣ Popular SLMs: ● DistilBERT ● Gemma ● GPT-4o mini ● Granite ● Llama ● Ministral ● Phi #LLM #SLM #GenAI www.ibm.com/think/topics...

submitted 80 days ago • 0 comments

Loved the new interface of #IntelliJ - great job by the underlying team 👍🏻 blog.jetbrains.com/idea/2024/10...

submitted 82 days ago • 0 comments

That’s interesting that Langfuse team didn’t think about caching prompts and using OLAP DB in early stages 🤔 Lessons learned: launch your product quickly and as it scales, evaluate and scale your architecture 👍🏻 langfuse.com/blog/2024-12...

submitted 83 days ago • 0 comments

Liked the # NA Sesion about using #OpenCost for managing GPU cost for the AI workload 👇 youtu.be/EAcoIZh118I?...

submitted 87 days ago • 0 comments

Which open source LLM you are using or planning for your next GenAI app? 1️⃣ Llama 2️⃣ Falcon 3️⃣ Gemma 4️⃣ Mistral 5️⃣ BLOOM Reply with your preference along with the rationale.

submitted 89 days ago • 0 comments

Shall I give up my Copilot ($10/month) and use ChatGPT Plus ($20/month) to experience SORA and new features? Thinking to use Cursor with ChatGPT 🤔 #ChatGPT #GitHubCopilot

submitted 90 days ago • 0 comments

The definition of golden path differs for different enterprises and so start your journey with an internal reference architecture for platform engineering to improve the development productivity incrementally. platformengineering.org/blog/how-to-... #platformengineering

submitted 92 days ago • 0 comments

Community initiatives like OPEA is great to build standards and solutions together 👍🏻 OPEA (Open Platform for Enterprise AI) is a framework that enables the creation and evaluation of open, multi-provider, robust, and composable generative AI (GenAI) solutions. opea-project.github.io

submitted 93 days ago • 0 comments

Finally, a platform where you feel free to express your views and ideas without any fear to get your account suspended for your opinions. Thanks @bsky.app team for building such platform and hopefully people in this community will respect each other for their opinions.

submitted 94 days ago • 0 comments

Going to check this framework out for AI apps development with LLMs for agentic workflows 👇 llmware.ai

submitted 94 days ago • 0 comments

AWS re:Invent '24 Takeaways from Keynote (Matt Garman) - Nova, S3, Q and Bedrock announcements are not to be missed 🧵 #aws #awsreinvent

submitted 97 days ago • 7 comments

Day 1 of AWS reInvent '24 (my 3rd consecutive year) 👇 🔹GenAI as a key theme across sessions, so Bedrock is full-fledged limelight 🔹 Key services S3, EKS, Aurora, Athena, IAM, etc. for best practices 🔹A lot of customers/partners case studies #AWSreInvent #AWSreInvent2024

submitted 99 days ago • 2 comments

Open source and novel approches in the #WebAI field serms promising 👍 WebLLM is a great initiative to start using LLM in the browser/client device itself. It opens up new avenues for innovative solutions for sure 👍 webllm.mlc.ai Source: WebAI Conference #WebLLM #Opensource

submitted 100 days ago • 0 comments

WebAI will make GenAI more accessible - nice to know 👇 #webai youtu.be/tF70o1Q8VkM?...

submitted 100 days ago • 0 comments

Interesting apps like msty.app to use LLMs locally will rise for local development with RAG support. But need more open source solutions with Apache/MIT license (Mstt license is restricted for personal usage).

submitted 100 days ago • 0 comments