Multi-Agent Systems
Teams of specialised agents that divide work, critique each other and deliver better results together.
Experiments in orchestrating several agents — supervisors, researchers, critics and executors — and the coordination patterns that make them reliable: hand-offs, shared state, debate and review loops.
- Experiments
- 2
- Open Source
- 2
- Technologies
- 7
- More to Explore
- ∞
Featured Multi-Agent Projects
A few highlighted experiments and prototypes.
- Multi-AgentFeatured
Research Crew
A multi-agent system that conducts in-depth research on any topic using specialized agents (researcher, critic, summarizer).
- LangChain
- CrewAI
- OpenAI
- Python
- Multi-Agent
Code Review Crew
Specialised agents that review pull requests for bugs, security issues and style, then merge their feedback.
- LangGraph
- GitHub API
- Claude
How My Agent Teams Collaborate
A typical architecture used in these experiments.
- Goal(User brief)
- Supervisor(Splits the work)
- Specialists(Run in parallel)
- Critic(Reviews output)
- Merge(Combine results)
- Deliver(Final answer)
Revise until the critic approves
All Multi-Agent Systems
Explore all my Multi-Agent experiments, from simple prototypes to advanced systems.
2 experiments
A multi-agent system that conducts in-depth research on any topic using specialized agents (researcher, critic, summarizer).
- LangChain
- CrewAI
- OpenAI
Specialised agents that review pull requests for bugs, security issues and style, then merge their feedback.
- LangGraph
- GitHub API
- Claude
Experiment · Learn · Build · Share
Let’s Build the Next Generation of Multi-Agent Systems
Check out the code, try the demos, or get in touch to collaborate on exciting ideas.