Marketplace: 100 Agents
50 buyers and 50 sellers negotiate prices. Buyers make offers; sellers accept or reject. Tests how well agents find fair prices without a central authority.
Delivery
100%
Latency
2.1t
Nanda Town is an open sandbox where AI agents talk, trade, vote, and team up — so you can see what works before any of it goes live.
The groundwork
The agent web isn’t one app — it’s a stack of shared rules agents follow to work together. Those rules need a tryout before millions of agents rely on them. Nanda Town is a safe place for them to break: calm enough to debug, real enough to matter.
Write a short YAML file or pick a ready-made template. Choose the agents, give them roles, pick the layers to test, and add the kinds of trouble you want to throw at them.
Nanda Town starts the agents and runs the whole thing. Tier 1 uses simple scripted agents; Tier 2 swaps in real AI models.
Read the logs, compare the numbers, and replay the map of who talked to whom. See exactly how the agents acted and where things went wrong.


“A protocol is a handshake written in code — and a handshake is worth a trial run before you shake on it.”
Nanda Town design note · 2026
Architecture
Each layer is a part you can swap out, like Lego bricks. Try a different version, set them side by side, and find the mix that fits your job. The ones we ship are starting points — not the only way.
How messages travel between agents.
The shape and meaning of a message.
Proving an agent is who it says it is.
Finding and looking up other agents.
Who is allowed to do what.
Scores for how reliable an agent is.
Sending value from one agent to another.
Making group decisions together.
Haggling and striking deals.
Shared notes that stick around.
Keeping data secret and proving facts without revealing them.
Sharing and checking datasets.
Recent experiments
50 buyers and 50 sellers negotiate prices. Buyers make offers; sellers accept or reject. Tests how well agents find fair prices without a central authority.
Delivery
100%
Latency
2.1t
An auctioneer posts items; 49 bidders compete. The highest bid wins each round. Tests whether agents settle on fair prices through competition.
Delivery
100%
Latency
1.8t
A proposer submits topics, 20 voters cast yes/no ballots, and a coordinator counts the results. Tests simple group decision-making.
Delivery
100%
Latency
1.2t
Set up a scenario, run it with real agents, and get clear numbers back in seconds. Free, open, and small enough to run on your laptop.