A List of Agentic Frameworks and Tools
I've collected the following list of Agentic Frameworks and Tools over time. Instead of them occupying 8,749 browser tabs, I made this list so I can find it myself again and hopefully someone else finds it useful.
GitHub Repos
Skyvern
Traditional approaches to browser automations required writing custom scripts for websites, often relying on DOM parsing and XPath-based interactions which would break whenever the website layouts changed. Skyvern relies on prompts in addition to computer vision and LLMs to parse items in the viewport in real-time.
My Take: I am keen to test this one. Given their commercial/cloud offering, I suspect the repo by itself would be limited to incentivize users toward the commercial offering.
OpenAI Swarm
The primary goal of Swarm is to showcase the handoff & routines patterns. It is not meant as a standalone library, and is primarily for educational purposes.
My Take: I've started building some example workflows with Swarm and it's very easy to understand and implement. Great to prove a concept, but would need additional tooling for production deployment.
AutoGPT
github.com/Significant-Gravitas/AutoGPT
AutoGPT is a powerful platform that allows you to create, deploy, and manage continuous AI agents that automate complex workflows. 167,000 Stars on GitHub shows the massive attention it received.
CrewAI
CrewAI is designed to enable AI agents to assume roles, share goals, and operate in a cohesive unit. Useful for solving complex problems by allowing smaller, specialized models to tackle sections of a problem.
MetaGPT
Software Company as Multi-Agent System. MetaGPT takes a one-line requirement as input and outputs user stories, competitive analysis, requirements, data structures, APIs, and documents.
Camel AI
Very active project exploring the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents. Could be a useful way to get advanced reasoning results using smaller models.
Academic Research
- Cognitive Architectures for Language Agents
- Self-RAG: Learning to Retrieve, Generate and Critique through Self-Reflection
- A Path Towards Autonomous Machine Intelligence by Yann LeCun
September 2026 update: for a more focused look at the harnesses I'd evaluate today, see The Best Open-Source Agent Harnesses in 2026.
Niël Malan
The Practical Futurist