Photo by editor
# Introduction
If you want to learn agent engineering rather than just read about it, the best way is still to fork the original repos, run them locally, and modify them for your own use. This is where the real learning happens. I’ve hand-picked the best 10, projects that are useful and widely recognized, so you can see how agent apps are being built today. So, let’s begin.
# 1. Open Claw
Open Claw (~343k ⭐) is the first one I’d point to if you want to see what the next wave of personal AI assistants might look like. It’s built as a personal assistant that runs on your own devices and connects to tools people already use, like WhatsApp, Telegram, Slack, Discord, Signal, and iMessage. What makes it interesting is that it’s not just a simple chat demo. It feels like a true companion product, with multi-channel support, acoustic features, and a broader ecosystem around expertise and control. If you want a repo that feels close to a real agent system, this is a solid place to start.
# 2. Open hands
Open hands (~70k ⭐) is a great repo to fork if your primary interest is in coding agents. It is built around AI-powered development and now has a wider ecosystem around it, including cloud, documents, CLI, SDKbenchmarking, and integration. This matters because you’re not just watching a demo. You can study the basic agent, check out the interface, and even see how the team thinks about evaluation and deployment. If you want to build or customize a coding assistant, this is one of the most practical repos to learn.
# 3. Browser Use
Using a browser (~85k ⭐) is one of the most useful projects if you want agents who can actually work on the web. The idea is simple: it makes websites easier for AI agents to use, so they can handle browser-based tasks with less friction. This makes it easier to experiment, since a lot of real agent work ends up in the browser anyway—form filling, research, navigation, and repetitive online tasks. It also has supporting repos and examples, making it easy to go from curiosity to something you can test in a real workflow.
# 4. Deer flow
Deer flow (~55k ⭐) Long Horizon is one of the more interesting projects if you want to understand agent systems. It is an open source superagent harness that brings together subagents, memory, sandboxes, skills and tools to research, code and create long tasks. So, it’s not just wrapping tool calls. It is trying to organize the entire structure around more complex agent behavior. If you want to see how modern agent systems are being built around memory, coordination and scalability, this is a very useful repo to fork.
# 5. Personnel
The staff (~48k ⭐) is still one of the easiest repos to understand if you want multi-agent orchestration without too much complexity. It’s a fast, flexible framework for multi-agent automation, and it’s built independently rather than on top of LangChain. The mental model is simple, the setup is accessible, and the documentation and examples are quite beginner-friendly. If you want a Python-first repo that you can fork and turn into something useful, CrewAI still deserves a spot near the top.
# 6. Langgraf
Lang Graf (~28k ⭐) is the repo to study when you want to understand the engineering side of agents, not just the shiny demo side. LangChain describes it as a low-level orchestration framework for long-running, stateful, controllable agents. It forces you to think in terms of graphs, state, control flow, and flexibility. This is especially useful if you want to go beyond simple prompt-plus-tool-call systems and understand how more serious agent runtimes are put together. It may not feel as quick to pick up as other reps, but it teaches a lot.
# 7. OpenAI Agents SDK
gave OpenAI Agents SDK (~20k ⭐) is a good option if you want something lightweight but still modern. It’s built as a compact framework for multi-agent workflows, and the documentation presents it as a production-ready path with a small set of useful building blocks. You get tools, handoffs, sessions, tracing, and real-time patterns without having to go through a big framework. If you like simple levels and direct controls, this is one of the best starter repos to explore.
# 8. Autogen
Autogen (~56k ⭐) is still one of the most important repos in the multi-agent space. Microsoft develops it as a programming framework for agent AI, and the documentation goes further into business workflows, research collaboration, and distributed multi-agent applications. It belongs on this kind of list because there is so much to learn from it. Orchestration ideas, agent conversation patterns, and framework design are all worth studying. It might not be the easiest starting point for everyone, but it’s still one of the most influential projects in the category.
# 9. GPT Researcher (~26k ⭐)
GPT researcher This is a great choice if you want to study a deep research agent rather than a general framework. It is an autonomous agent for intensive research using any major language model (LLM) provider, and its surrounding content demonstrates how it handles multi-agent research and report generation. It gives you a clear workflow to study from start to finish. You can see planning, browsing, source collection, synthesis, and reporting all in one place. If you want something concrete rather than abstract, this is one of the most forkable repos on the list.
# 10. Lying down
lying down (~22k ⭐) stands out because it puts memory and state at the heart of agent design. Repo describes it as a platform for building stateful agents with advanced memory that can learn and improve over time. This is an important angle because many agent repos focus mostly on orchestration. Lying down enlarges the image. This is a good repo to explore if you want agents that persist, remember, and evolve instead of starting from scratch each time. For a memory-centric agent task, this is one of the more exciting projects of today.
# wrap up
All ten are cloneable, but they teach different things when you actually run them and start changing the code. This is where the real learning begins.
Kanwal Mehreen is a machine learning engineer and a technical writer with a deep passion for AI along with data science and medicine. He co-authored the e-book “Maximizing Productivity with ChatGPT”. As a Google Generation Scholar 2022 for APAC, she is a champion of diversity and academic excellence. She is also recognized as a Teradata Diversity in Tech Scholar, a Mitacs Globalink Research Scholar, and a Harvard WeCode Scholar. Kanwal is a passionate advocate for change, having founded FEMCodes to empower women in STEM fields.