
Shubham Saboo
@Saboo_Shubham_
Followers
86K
Following
44K
Media
3K
Statuses
15K
Daily tips and tutorials on LLMs, RAG and AI Agents | Author of books on GPT-3 & Neural Search in Production | DM open for collaboration
AI Agents & RAG Tutorials →
Joined June 2020
This is crazy! . Just made it to top trending developers list on @github. Building in public and Opensource AI is the way to go. While others charge $10,000+ for AI courses. I opensourced 100+ AI Agents, MCP Agents, and RAG tutorials for free.
28
15
218
RT @Saboo_Shubham_: Grok 4 builds a multi-agent VC team that provides feedback on the startup pitch deck just by looking at Awesome LLM App….
0
13
0
Stay tuned for more such posts, 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 🌟.
1
0
7
@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.
0
0
8
@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 🌟.
1
0
18
@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:
2
5
53
@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.
4
3
27
@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.
1
2
29
@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.
2
4
28
@Kimi_Moonshot 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.
2
1
43
Kimi k2 by @Kimi_Moonshot is a SOTA AI coding model that gives amazing 1 shot results at coding prompts.
4
1
58
This is a bad take. Claude Code is miles ahead for actual development work. Superior context awareness, better code understanding, and seamless workflow integration. Grok CLI might be flashy but Claude Code gets the job done.
Grok CLI >>> Cursor and Claude Code. We wanted an IDE for @xai's @grok so we did something meta: we prompted the newly released Grok 4 to create. Grok CLI itself!. Grok CLI can:.1. Modify local files and use the shell.2. Go through huge codebases and fix them.3. Persist for
8
6
74
Stay tuned for more such interesting posts → @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 🌟.
1
0
6