resources

Agentic AI

What is it?

Agentic AI refers to artificial intelligence systems that exhibit a sense of agency or autonomy in their decision-making processes. These systems are designed to act independently, make decisions, and take actions based on their understanding of the environment and their goals. Agentic AI is characterized by its ability to perceive, reason, and act in a way that mimics human-like agency, often involving complex cognitive processes and adaptive behaviors.

Resources

Agentic Framework Lists

Great collection of AI Agent related frameworks:
https://www.awesomepython.org/?c=agentic-ai

Specific AI Agent frameworks:
https://www.awesomepython.org/?q=agent-framework (Agent frameworks)

Specific AI Agent support tasks:
https://www.awesomepython.org/?q=agent-framework (Agent frameworks) https://www.awesomepython.org/?q=llm-observability (LLM observability)
https://www.awesomepython.org/?q=llm-evaluation (LLM evaluation)
https://www.awesomepython.org/?q=llm-guardrails (LLM guardrails)
https://www.awesomepython.org/?q=llm-structured-output (LLM structured output)

Smolagents LLM Leaderboard
https://huggingface.co/spaces/smolagents/smolagents-leaderboard

Agentic GitHub Repos

(Updated Apr 2025)

Microsoft Autogen: A framework for building AI agents and applications
- https://github.com/microsoft/autogen
- https://microsoft.github.io/autogen/stable/
CrewAI: Fast and Flexible Multi-Agent Automation Framework
- https://github.com/crewaiinc/crewai
- https://www.crewai.com/
Agno: a lightweight library for building Agents with memory, knowledge, tools and reasoning.
- https://github.com/agno-agi/agno
- https://docs.agno.com/introduction
Agent Development Kit (ADK): An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents
- https://github.com/google/adk-python
- https://google.github.io/adk-docs/
Pydantic AI: Agent Framework / shim to use Pydantic with LLMs
- https://github.com/pydantic/pydantic-ai
- https://ai.pydantic.dev/
OpenAI Agents SDK: A lightweight, powerful framework for multi-agent workflows
- https://github.com/openai/openai-agents-python
- https://openai.github.io/openai-agents-python/
smolagents: a library that enables you to run powerful agents in a few lines of code.
- https://github.com/huggingface/smolagents
- https://huggingface.co/docs/smolagents/index
OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
- https://github.com/camel-ai/owl
- https://hypnotic-mind-6bd.notion.site/OWL-Optimized-Workforce-Learning-for-General-Multi-Agent-Assistance-in-Real-World-Task-Automation-1d4004aeb21380158749c7f84b20643f
- https://arxiv.org/abs/2303.17760
CAMEL: an open-source community dedicated to finding the scaling laws of agents
- https://github.com/camel-ai/camel
- https://arxiv.org/abs/2303.17760
LangGraph: Build resilient language agents as graphs.
- https://github.com/langchain-ai/langgraph
- https://langchain-ai.github.io/langgraph/
Upsonic: The most reliable AI agent framework that supports MCP.
- https://github.com/upsonic/upsonic
- https://docs.upsonic.ai/introduction
Atomic Agent: Building AI agents, atomically
- https://github.com/brainblend-ai/atomic-agents
- https://ai.gopubby.com/want-to-build-ai-agents-c83ab4535411
AG2 (formerly AutoGen): an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks
- https://github.com/ag2ai/ag2
- https://ag2.ai/
BeeAI Framework: Build production-ready AI agents in both Python and Typescript
- https://github.com/i-am-bee/beeai-framework
- https://i-am-bee.github.io/beeai-framework/#/
Langflow: a powerful tool for building and deploying AI-powered agents and workflows.
- https://github.com/langflow-ai/langflow
- https://docs.langflow.org/
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
- https://github.com/sakanaai/ai-scientist-v2
- https://sakana.ai/ai-scientist-first-publication/
- https://arxiv.org/abs/2504.08066
Storm: LLM-powered knowledge curation system that researches a topic and generates a full-length report
- https://github.com/stanford-oval/storm
- https://storm.genie.stanford.edu/

Readings

OpenAI A Practical Guide to Building Agents - Apr 2025
https://cdn.openai.com/business-guides-and-resources/a-practical-guide-to-building-agents.pdf

Building effective agents by Anthropic - Dec 2024
https://www.anthropic.com/research/building-effective-agents

Sample from Chip Huyen’s book AI Engineering - Jan 2025
https://huyenchip.com//2025/01/07/agents.html

Hugging Face blog on SmolAgents - Feb 2025
https://huggingface.co/blog/smolagents
https://huggingface.co/docs/smolagents

AI Agents: How to build Digital Workers - Nov 2024 https://medium.com/@alfredosone/ai-agents-how-to-build-digital-workers-4fe68bb20348

Google whitepaper on Agents (Overview and tool usage) - Feb 2025
https://www.kaggle.com/whitepaper-agents

Google companion whitepaper on Agents (AgentOps and Eval focus) - Feb 2025
https://www.kaggle.com/whitepaper-agent-companion

Weaviate: What Are Agentic Workflows? Patterns, Use Cases, Examples, and More - Mar 2025
https://weaviate.io/blog/what-are-agentic-workflows

Weaviate Agentic Architectures for RAG - Mar 2025
https://8738733.fs1.hubspotusercontent-na1.net/hubfs/8738733/eBooks/Weaviate%20Agentic%20Architectures-ebook.pdf

OpenAI tools for building agents - Mar 2025
https://openai.com/index/new-tools-for-building-agents/

Building an AI Agent with Memory and Adaptability - Mar 2025
https://diamantai.substack.com/p/building-an-ai-agent-with-memory

A Visual Guide to LLM Agents
https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-llm-agents

OpenAI - Common agentic patterns
https://github.com/openai/openai-agents-python/blob/main/examples/agent_patterns/README.md

Cohere: AI agents, Everything you need to know - Mar 2025 https://cohere.com/blog/ai-agents

Cohere: Building AI agents, 5 common hurdles and fixes - Mar 2025 https://cohere.com/blog/building-ai-agents

OpenAI Cookbook - Agents
https://cookbook.openai.com/topic/agents

Courses

Huggingface Agents Course (2025)
https://github.com/huggingface/agents-course https://huggingface.co/agents-course
https://huggingface.co/learn/agents-course/unit0/introduction https://huggingface.co/learn/agents-course/unit2/smolagents/introduction https://huggingface.co/learn/agents-course/unit2/llama-index/introduction https://huggingface.co/learn/agents-course/unit2/langgraph/introduction

Self-paced GenAI learning guide by Google (incl link to Agents whitepaper above) - Nov 2024
https://www.kaggle.com/learn-guide/5-day-genai

Building Agentic RAG with Llamaindex
https://learn.deeplearning.ai/courses/building-agentic-rag-with-llamaindex/

AI Agentic Design Patterns with AutoGen
https://learn.deeplearning.ai/courses/ai-agentic-design-patterns-with-autogen/

AI Agents in LangGraph
https://learn.deeplearning.ai/courses/ai-agents-in-langgraph/

AI Agents for beginners (Microsoft)
https://github.com/microsoft/generative-ai-for-beginners/tree/main/17-ai-agents

Cohere LLM University
https://cohere.com/llmu

Microsoft - AI Agents for Beginners - A Course
https://microsoft.github.io/ai-agents-for-beginners/

Papers

A compilation of the best multi-agent papers
https://github.com/kyegomez/awesome-multi-agent-papers

Agent paper collection by m-ric
https://huggingface.co/collections/m-ric/agents-65ba776fbd9e29f771c07d4e

Autonomous Agents-research papers, updated daily
https://github.com/tmgthb/Autonomous-Agents

Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
https://arxiv.org/abs/2501.09136

Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks (Microsoft)
https://arxiv.org/abs/2411.04468

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
https://arxiv.org/abs/2408.06292

The Rise and Potential of Large Language Model Based Agents: A Survey
https://arxiv.org/abs/2309.07864

TODO: more papers

LLM Rankings

https://openrouter.ai/rankings

https://lmarena.ai/?leaderboard

https://huggingface.co/spaces/smolagents/smolagents-leaderboard

https://huggingface.co/spaces/gaia-benchmark/leaderboard