Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Shubham Saboo Profile picture
@Saboo_Shubham_
Jul 11 • 10 tweets • 4 min read • Read on X
Scrolly
After DeepSeek R1, there's new Claude 4 level model from China that outperforms DeepSeek v3, Qwen and OpenAI GPT-4.1

Meet Kimi k2 - 1 trillion parameter model purpose-built for agentic workflows with native MCP integration.

100% Opensource and FREE to try. Let that sink in. Image
Kimi k2 by @Kimi_Moonshot is a SOTA AI coding model that gives amazing 1 shot results at coding prompts.

Kimi k2 comes in two variants:

→ K2-Base for researchers who want full control for fine-tuning and custom solutions.

→ K2-Instruct for drop-in general-purpose chat and AI Agent experiences.

@Kimi_Moonshot Kimi K2 beats Claude Sonnet 4 and GPT-4.1 across coding benchmarks.

65.8% on SWE-bench Verified vs Claude's 50.2% and GPT's 40.8%.

SOTA performance in math, coding, and AI Agent tasks among non-thinking models. Image
@Kimi_Moonshot Great for Agentic workflows.

Kimi K2 performed 16 tool calls to generate statistics, visualizations, and an interactive webpage.

Complete analysis from raw data to insights in seconds.

@Kimi_Moonshot Another coding example: 3D Particle Galaxy Simulation built with Kimi k2

@Kimi_Moonshot Kimi K2 runs directly in your terminal.

It understands your environment, decides what actions to take, and executes them seamlessly.

It just built a 3D Minecraft web version from a single prompt.
@Kimi_Moonshot Also available as an API:

- $0.15 / million input tokens (cache hit)
- $0.60 / million input tokens (cache miss)
- $2.50 / million output tokens

Almost ~5x cheaper than Claude 4 Sonnet and Gemini 2.5 Pro.

GitHub Repo: github.com/MoonshotAI/Kim…
@Kimi_Moonshot Stay tuned for more details, follow me → @Saboo_Shubham_

I have created 100+ AI Agents and RAG tutorials, 100% free and opensource.

P.S: Don't forget to star the repo to show your support 🌟

github.com/Shubhamsaboo/a…
@Kimi_Moonshot 100+ free step-by-step tutorials with code covering:

🚀 AI Agents
📀 RAG Systems
🗣️ Voice AI Agents
🌐 MCP AI Agents
🤝 Multi-agent Teams
🎮 Autonomous Game Playing Agents

P.S: Don't forget to subscribe for FREE to access future tutorials.

theunwindai.com

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Shubham Saboo

Shubham Saboo Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @Saboo_Shubham_

Shubham Saboo Profile picture
Jul 10
Grok 4 builds an AI Investment Agent team just by going through the documentation.

Replit lets me run, test and deploy that agent team directly from the browser.

All of this in less than 2 mins.
I have created 100+ AI Agents and RAG tutorials, 100% free and opensource.

P.S: Don't forget to star the repo to show your support 🌟
github.com/Shubhamsaboo/a…
100+ free step-by-step tutorials with code covering:

🚀 AI Agents
📀 RAG Systems
🗣️ Voice AI Agents
🌐 MCP AI Agents
🤝 Multi-agent Teams
🎮 Autonomous Game Playing Agents

P.S: Don't forget to subscribe for FREE to access future tutorials.

theunwindai.comImage
Read 4 tweets
Shubham Saboo Profile picture
Jul 6
Build a Customer Support Ticket Agent with Structured output using Google Agent Development Kit.

100% Opensource code with step-by-step tutorial:
1. Install the necessary Python Libraries

Run the following commands to install the required libraries: Image
2. Set Up Project Structure

Create this folder structure: Image
Read 9 tweets
Shubham Saboo Profile picture
Jul 5
Build an AI Agent with Structured Output using Google ADK (step-by-step instructions):
What Are Structured Outputs?

Think of structured outputs as a strict dress code for your AI agent's responses.

Instead of getting random, unpredictable text, you get perfectly formatted JSON every single time.

Let's build our AI Agent with structured output 👇 Image
1. Install the necessary Python Libraries

Run the following commands to install the required libraries: Image
Read 8 tweets
Shubham Saboo Profile picture
Jun 21
This Chinese AI model just changed document OCR forever.

It can parse complex documents with text, tables, formulas and figures in parallel simultaneously using task-specific prompts.

100% opensource.
Dolphin uses a smart two-stage parsing approach.

Stage 1: Analyzes page layout and generates element sequence in natural reading order.

Stage 2: Parses all document elements simultaneously using task-specific prompts. Image
You can try Dolphin's document parsing capabilities right now with live demo on GitHub.

GitHub Repo: github.com/bytedance/Dolp…
Read 4 tweets
Shubham Saboo Profile picture
Jun 10
This is crazy!

Meet the world's first fully Agentic Download Agent and AI Drive.

It can literally search, download, and organize any files instantly in the AI drive from just a single prompt.

Works with PDFs, images, videos, music, and Office documents.

3 wild examples:
1. Batch Download Images Instantly:

The Download Agent searches trusted platforms like Pixabay and Unsplash, gathers your images, and places them in a dedicated folder in your AI Drive.

One prompt does it all—no more tedious clicking or sorting.
2. Effortless PDF Collection for Research:

The Download Agent reads the post, locates every paper, downloads them, and organizes everything into a neatly named folder.

Files are even renamed to match their titles, making future reference effortless.
Read 5 tweets
Shubham Saboo Profile picture
Jun 7
Build an Agentic RAG systems that can Reason using Claude 4 and OpenAI Embedder (step-by-step instructions):
1. Install the necessary Python Libraries

Run the following commands from your terminal to install the required libraries: Image
2. Import necessary libraries

• @AgnoAgi framework provides the agent infrastructure
• @streamlit creates the web interface
• Environment variables for secure API key management Image
Read 14 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

Send Email!

:(