Post

How to get URL link on X (Twitter) App

On the Twitter thread, click on or icon on the bottom
Click again on or Share Via icon
Click on Copy Link to Tweet
Paste it above and click "Unroll Thread"!
More info at Twitter Help

Shubham Saboo

Mar 20 • 7 tweets • 4 min read • Read on X

Scrolly

5 AI agent frameworks to build multi-agent applications.

100% opensource.

They aren't LangChain, Crew AI, or OpenAI Agents SDK.

1. Motia is an AI agent framework is built for Software Engineers. Build agents in Python, TypeScript, JavaScript or Ruby.

github.com/MotiaDev/motia

2. Agno is a lightweight Python library for building Multimodal Agents with memory, knowledge, and tools.

• ~10,000x faster than LangGraph
• Build teams of specialized agents
• Make Agents respond with structured data

github.com/agno-agi/agno

3. AWS Multi-Agent Orchestrator is a flexible framework to build multi-agents AI applications.

4. • Routes queries to the most suitable agent
• Fully implemented in both Python and TypeScript
• Variety of ready-to-use agents

github.com/awslabs/multi-…

4. PydanticAI is a Python based agent framework to build production grade applications.

• Model-agnostic
• Python-centric Design
• Structured outputs

github.com/pydantic/pydan…

5. AutoAgent creates and deploys fully-automated AI agents with no-code. Build multi-agent teams and agentic RAG apps from simple prompts.

It is equipped with a native self-managing vector database, outperforms industry-leading solutions like LangChain.

github.com/HKUDS/AutoAgent

I have created 50+ AI Agents and RAG tutorials, 100% free and opensource.

Two simple steps to get started:
1. Subscribe to Unwind AI (for free): theunwindai.com
2. Star the repo: github.com/Shubhamsaboo/a…

New AI Agents and RAG tutorials added every week.

https://x.com/Saboo_Shubham_/status/1902547400893591584

If you find this useful, RT to share it with your friends.

Don't forget to follow me @Saboo_Shubham_ for more such LLM tips and AI Agent, RAG tutorials.

https://x.com/Saboo_Shubham_/status/1902547400893591584

• • •

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

This Thread may be Removed Anytime!

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

More from @Saboo_Shubham_

Shubham Saboo

@Saboo_Shubham_

Apr 18

I built an MCP AI Agent using Gemini Flash 2.5 with access to AirBnB and Google Maps in just 30 lines of Python Code.

100% Opensource Code.

Here's the full Opensource code.

🌟 Star the repo for more: github.com/Shubhamsaboo/a…

Read 4 tweets

Shubham Saboo

@Saboo_Shubham_

Apr 16

OpenAI just launched o3 and o4-mini with agentic tool use.

It's been just a few hours, and the internet is filled with incredible AI examples.

10 wild examples:

https://x.com/emollick/status/1912597487287705965

1. o3 creates a movie without video tools by sketching each frame of an otter and airplane scene and stitching them into a GIF, all in one shot.

https://x.com/emollick/status/1912597487287705965

2. o3 and o4-mini nailed the coding vibe check

Read 13 tweets

Shubham Saboo

@Saboo_Shubham_

Apr 16

Web Action AI Agent that doesn’t just scrape but finds the data you need.

Firecrawl launched FIRE-1, an AI agent that navigates complex websites, interacts with buttons, fills forms, and gathers data beyond traditional scraping.

No manual steps required.

FIRE-1 AI Agent is available to use on Firecrawl starting today.

Learn more about it here: firecrawl.dev/blog/launch-we…

Read 4 tweets

Shubham Saboo

@Saboo_Shubham_

Apr 14

Let's build & deploy production grade Gemini AI Agents in 3 simple steps using Google Cloud Vertex AI Engine.

Works with LangChain, LlamaIndex, and other Agent frameworks.

1. Install Vertex AI SDK for Python

Install the latest version of the Vertex AI SDK for Python as well as extra dependencies related to Agent Engine and LangChain:

2.1 Import Libraries and Define Model

Read 8 tweets

Shubham Saboo

@Saboo_Shubham_

Apr 4

Huge AI agent updates from Anthropic, PayPal, Windsurf, Cognition AI, and more.

Multiple agents working in parallel was the highlight.

1. Devin 2.0 is here with a new agent-native IDE experience. It lets you run parallel Devins to take on multiple tasks at once. Starts at $20.

2. Genspark is a general-purpose superagent that can think, plan, act, and use tools to handle all your everyday tasks. Rather than using a computer in a sandboxed VM, it uses its in-house system to directly call APIs whenever needed.

Outperforms Manus AI and OpenAI Operator.

Read 12 tweets

Shubham Saboo

@Saboo_Shubham_

Mar 29

Multi-agent team need long-term memory to maintain context and learn continuously.

5 frameworks for AI agent memory.

100% opensource.

1. Mem0 is an intelligent memory layer for AI agents, enabling them to actively learn from and adapt to user interactions over time.

It combines LLMs with vector storage:
- LLMs process key information from conversations
- Vector storage performs semantic search