Agentic AI P2P Framework

Understanding the Office Space in AgentSpaces

A peer is one process running the library, whether it be a microservice process, a Python script, or even an agent in the browser. All peers have a secure Ed25519 identity, can join one or more groups, and register the spaces they take part in. Peers can relay for others, traversing networks, with end-to-end encryption between the originator and its group. This enables AgentSpaces to have a robust P2P fabric, with many secure groups, safeguarding appropriately.

A space is a replicated tuple space, where entries get a TTL, and foundational APIs for working with records. Capabilities get layered on top, enabling peers to advertise if they can do more: build quorums, vote, calculate aggregates, provide strong consistency, and even use the P2P network for learning! Read the architecture guide to learn more about the types of systems AgentSpaces enables.

The vocabulary, and the mechanism behind each word

The office metaphor helps us understand how these agents can work together in groups.

Build Agentic Fleets, with your framework

Agents stay ordinary code in the framework you already use. Each host binds them to the same spaces in its own idiom, and every host shares one signed wire.

Spring AI×

• Tools, advisors and chat memory on the fleet
• FleetChatModel serves model calls fleet-wide
• MCP, embeddings and observations wired in

GitHub sourceOpen in the guide

Python×

• @agent and @space_take on plain methods
• The same signed CBOR wire as the JVM
• Ordered takes, joins and reduces from 0.4.0

GitHub sourceOpen in the guide

Embabel×

• @Agent goals and actions become AgentCards
• Fleet skills become planner actions
• One annotation joins an action to the fleet

GitHub sourceOpen in the guide

Micronaut×

• Beans publish AgentCards, data publishes AssetCards
• @Client resolves services through the fleet
• Micronaut 5.2 on JDK 25

GitHub sourceOpen in the guide

Clojure×

• defagent: one form, a clause per verb
• Maps in and out, a keyword :where DSL
• On Clojars as agentspaces-clj 0.4.0

GitHub sourceOpen in the guide

LangChain4j×

• Fleet features on any JVM host
• No application framework on the classpath
• CLI agents, embedded services, batch jobs

GitHub sourceOpen in the guide

TypeScript×

• Stage-3 decorators: @agent, @spaceTake, @ballot
• Watches as EventEmitter or async iterator
• The in-flight take rides AsyncLocalStorage

GitHub sourceOpen in the guide

JavaScript and celld×

• One Peer: browser, Workers, Deno, Bun, Node
• WebSocket and TCP transports
• Connector cells on celld, per the JS design

GitHub sourceOpen in the guide

Groovy×

• Java annotations bind as they are
• FleetScript: a one-file peer
• fleet { } and agent(name) { } closures

GitHub sourceOpen in the guide

Get your agents their own spaces today

Add an annotation, join an AgentSpace. AgentSpaces is open source, more integrations, libraries, and languages getting added routinely.

@SpaceAgent(description = "Ships orders from the shared space")
public class Fulfiller {

    @SpaceTake(lease = "10m")         // crash => order reappears
    public Shipment ship(Order order) {
        return new Shipment(order.orderId(), order.item(), "fulfiller");
    }

    @BidFunction                      // AUCTION spaces only
    public double bid(Order order) {
        return estimatedTokens(order) * modelCostPerToken();
    }
}

<dependency>
  <groupId>ai.badmonkey.agentspaces</groupId>
  <artifactId>agentspaces-spring-boot-starter</artifactId>
  <version>0.2.0</version>
</dependency>

<!-- or import agentspaces-dependencies 0.2.0 as a BOM and drop the version -->

# a Python peer takes the same typed work off the same space
from agentspaces.space import entry
from agentspaces.agents import Binder, agent, space_take

@entry("ai.badmonkey.agentspaces.examples.Order#v1")
@dataclass
class Order:
    orderId: str
    item: str

@agent("py-fulfiller", description="Ships orders")
class Fulfiller:
    @space_take("work", lease="10m")      # take, call, complete with the result
    def ship(self, order: Order) -> Shipment:
        return Shipment(order.orderId, order.item, "py-worker")

Binder(peer).bind(Fulfiller())           # the same loops the Java binder runs