Ideas building the future of AI agents. A 100% free event for LATAM tech communities.
The next generation of autonomous systems is built on open protocols, secure connectivity gateways, MicroVM runtime isolation, and verifiable governance.
Model Context Protocol (MCP) is a protocol for seamless integration between LLM applications and external data sources.
Open standard that unifies how LLM-powered applications discover, authenticate, and connect seamlessly to external tools and data sources.
AGENTS.md is a simple, open format for guiding coding agents.
Declarative, repository-native open format to guide coding agents on architecture, conventions, build commands, and verification workflows.
Agent2Agent (A2A) is an open protocol that enables AI agents to communicate, collaborate, and securely exchange information and tasks across different platforms and frameworks.
Open interoperability protocol enabling agents built across diverse frameworks to collaborate, delegate tasks, and exchange context securely.
agentgateway enables secure, scalable connections between AI agents, models, tools, and APIs across ecosystems.
Secure, scalable connectivity plane bridging AI agents, foundation models, tools, and enterprise APIs across multi-cloud ecosystems.
Agent Router is an open source AI gateway built on Envoy that connects applications to models and MCP tools while platform teams manage access, routing, and usage.
Envoy-based open source AI gateway connecting applications to models and MCP tools while platform teams enforce access, routing, and usage policies.
MicroVM isolation for every agent session, local or cloud. Network and filesystem locked down at the runtime.
Dedicated MicroVM isolation for every agent session—local or cloud—with network and filesystem access locked down directly at the runtime layer.
Code-first toolkit for building, orchestrating, evaluating, and deploying sophisticated multi-agent systems.
Modular, code-first framework to design, orchestrate, test, and deploy single and multi-agent workflows with native MCP tools, A2A interoperability, and bidirectional streaming.
Hierarchical, sequential, parallel, and loop orchestrations with context engineering, memory, and state management.
Reference architectures for production agents: supervisor/sub-agent delegation, deterministic and dynamic routing, long-term memory, context compaction, and human-in-the-loop workflows.
Unlocking agent autonomy in production demands governance by design: least-privilege policies, verifiable agent identity, audited MCP/A2A tool calls, and MicroVM-confined execution.
AI Agents Day is made possible by global leaders in agent infrastructure and is a 100% free event for tech communities across Latin America.
