Picture by Editor
# Introduction
If you wish to study agent engineering by doing as an alternative of simply studying about it, the easiest way remains to be to fork actual repos, run them domestically, and alter them to your personal use. That is the place the true studying occurs. I’ve hand-picked one of the best 10 ones, the initiatives which are each helpful and widely known, so you’ll be able to see how agent apps are being constructed at present. So, let’s get began.
# 1. OpenClaw
OpenClaw (~343k ⭐) is the one I might level to first if you wish to see what the subsequent wave of non-public AI assistants would possibly seem like. It’s constructed as a private assistant that runs by yourself units and connects to the instruments individuals already use, like WhatsApp, Telegram, Slack, Discord, Sign, and iMessage. What makes it attention-grabbing is that it’s not only a easy chat demo. It looks like an actual assistant product, with multi-channel help, voice options, and a broader ecosystem round abilities and management. If you would like a repo that feels near an actual agent system, this can be a robust place to start out.
# 2. OpenHands
OpenHands (~70k ⭐) is a superb repo to fork in case your important curiosity is coding brokers. It’s constructed round AI-driven growth and now has a wider ecosystem round it, together with cloud, docs, CLI, SDK, benchmarking, and integrations. That issues as a result of you aren’t simply one demo. You’ll be able to examine the core agent, test the interface, and in addition see how the crew thinks about analysis and deployment. If you wish to construct or customise a coding assistant, this is likely one of the most sensible repos to study from.
# 3. browser-use
browser-use (~85k ⭐) is likely one of the most helpful initiatives in order for you brokers that may truly do issues on the internet. The thought is straightforward: it makes web sites simpler for AI brokers to make use of, to allow them to deal with browser-based duties with much less friction. That makes it simple to experiment with, since a variety of actual agent work results in the browser anyway — type filling, analysis, navigation, and repetitive on-line duties. It additionally has supporting repos and examples, which makes it simpler to go from curiosity to one thing you’ll be able to check in an actual workflow.
# 4. DeerFlow
DeerFlow (~55k ⭐) is likely one of the extra attention-grabbing initiatives if you wish to perceive long-horizon agent programs. It’s an open-source super-agent harness that brings collectively sub-agents, reminiscence, sandboxes, abilities, and instruments to analysis, code, and create throughout longer duties. So, it’s not simply wrapping device calls. It’s making an attempt to handle the complete construction round extra advanced agent conduct. If you wish to see how trendy agent programs are being constructed round reminiscence, coordination, and extensibility, this can be a very helpful repo to fork.
# 5. CrewAI
CrewAI (~48k ⭐) remains to be one of many best repos to know in order for you multi-agent orchestration with out an excessive amount of complexity. It’s a quick, versatile framework for multi-agent automation, and it’s constructed independently reasonably than on prime of LangChain. The psychological mannequin is straightforward, the setup is approachable, and the docs and examples are pleasant sufficient for inexperienced persons. If you would like a Python-first repo you can fork and switch into one thing helpful, CrewAI nonetheless deserves a spot close to the highest.
# 6. LangGraph
LangGraph (~28k ⭐) is the repo to check whenever you need to perceive the engineering facet of brokers, not simply the flashy demo facet. LangChain describes it as a low-level orchestration framework for long-running, stateful, controllable brokers. It pushes you to assume by way of graphs, state, management movement, and resilience. It’s particularly helpful if you wish to transfer past easy prompt-plus-tool-call programs and perceive how extra severe agent runtimes are put collectively. It might not really feel as fast to select up as another repos, but it surely teaches rather a lot.
# 7. OpenAI Brokers SDK
The OpenAI Brokers SDK (~20k ⭐) is an effective choice in order for you one thing light-weight however nonetheless trendy. It’s constructed as a compact framework for multi-agent workflows, and the docs current it as a production-ready path with a small set of helpful constructing blocks. You get instruments, handoffs, classes, tracing, and realtime patterns with out having to wade via an enormous framework. In case you like easy surfaces and direct management, this is likely one of the higher starter repos to discover.
# 8. AutoGen
AutoGen (~56k ⭐) remains to be probably the most vital repos within the multi-agent house. Microsoft frames it as a programming framework for agentic AI, and the docs go additional into enterprise workflows, analysis collaboration, and distributed multi-agent functions. It belongs in this type of listing as a result of there’s a lot to study from it. The orchestration concepts, agent dialog patterns, and framework design are all value finding out. It might not be the only place to begin for everybody, however it’s nonetheless probably the most influential initiatives within the class.
# 9. GPT Researcher (~26k ⭐)
GPT Researcher is a superb selection if you wish to examine a deep-research agent as an alternative of a basic framework. It’s an autonomous agent for deep analysis utilizing any massive language mannequin (LLM) supplier, and its surrounding materials exhibits the way it handles multi-agent analysis and report era. This provides you one clear workflow to check from begin to end. You’ll be able to see planning, searching, supply gathering, synthesis, and reporting multi functional place. If you would like one thing concrete reasonably than summary, this is likely one of the most forkable repos on the listing.
# 10. Letta
Letta (~22k ⭐) stands out as a result of it places reminiscence and state on the middle of the agent design. The repo describes it as a platform for constructing stateful brokers with superior reminiscence that may study and enhance over time. This is a crucial angle as a result of a variety of agent repos focus totally on orchestration. Letta widens the image. It’s a good repo to discover in order for you brokers that persist, keep in mind, and evolve as an alternative of beginning recent each time. For memory-focused agent work, it is likely one of the extra attention-grabbing initiatives to fork at present.
# Wrapping Up
All ten are value cloning, however they train various things when you truly run them and begin altering the code. That’s the place the true studying begins.
Kanwal Mehreen is a machine studying engineer and a technical author with a profound ardour for information science and the intersection of AI with drugs. She co-authored the book “Maximizing Productiveness with ChatGPT”. As a Google Technology Scholar 2022 for APAC, she champions variety and educational excellence. She’s additionally acknowledged as a Teradata Range in Tech Scholar, Mitacs Globalink Analysis Scholar, and Harvard WeCode Scholar. Kanwal is an ardent advocate for change, having based FEMCodes to empower girls in STEM fields.
