event-driven

Mycelium is an open-source, event-driven platform enabling AI agents to collaborate in a real-time virtual office, featuring WebSocket streaming, SQLite persistence, and production-grade guardrails for developers.

The article argues that long-running development agents should be event-driven to detect useful changes from unexpected sources via broadcasts like EigenFlux, rather than polling repositories daily, and stresses verifying sources before acting.

The post discusses a gap in the Model Context Protocol (MCP) that could be addressed by adding webhook support, allowing connected MCP servers to ping agents with events.

The article describes Pizza, an open-source event-driven AI agent that uses event sourcing and state machines to create a robust and auditable agent architecture with features like forking conversations and self-optimization.

An engineer reflects on repeatedly building webhook integration systems, detailing the hidden complexity of signature verification, deduplication, buffering, and reconciliation crons, and argues that webhook notifications are not a reliable substitute for a complete ordered data log.

This tutorial teaches how to implement the Outbox Pattern in Go and PostgreSQL to ensure reliable event publishing in distributed systems, including building a relay service and handling at-least-once delivery.

Magents is an open-source Python framework for simulating and backtesting multiple trading strategies in one system, with isolated strategy pods, an event-driven engine, and central risk controls.

This article provides a detailed breakdown of the Hermes Agent architecture, including the event bus, adapter layer, GatewayRunner core scheduler layer, etc., revealing the design pattern of the Agent as a stateful, event-driven runtime.

The author argues that chat-first AI tools are insufficient for building autonomous agent workflows and describes alternative primitives like scheduled triggers and sub-agent delegation, advocating for a paradigm shift from 'chat with tools' to 'autonomous processes that use LLMs'.

This paper proposes EHHN, an event-driven heterogeneous hypergraph network for object-centric next activity prediction in service processes, achieving state-of-the-art accuracy and memory efficiency on four benchmarks.

This article provides an end-to-end example of a durable AI agent using Google's Gemini Enterprise Agent Platform. It covers patterns for state machines, event-driven agents, and multi-agent delegation for long-running tasks like employee onboarding.

LangChain's loop engineering playbook replaces prompt engineering with four nested loops - agent, verification, event-driven, and hill-climbing - enabling AI agents to automatically improve themselves over time. The post argues that building self-optimizing loops is now the key competitive advantage, not using better models.

This paper evaluates multi-agent orchestration architectures (DAG Plan and Execute, ReAct) at enterprise scales and introduces a Task Manager for continuous event-driven operation, showing improvements in latency and correctness.

This blog post by Sydney Runkle explains the art of loop engineering for building reliable LLM agents using LangChain primitives, covering four levels of loops: agent loop, verification loop, event-driven loop, and hill climbing loop.

This article discusses the inefficiency of polling in OpenClaw agents and introduces a plugin that moves event detection outside the agent loop, resulting in significant reductions in source calls and token usage.

Nader Dabit predicts that by end of year, over 95% of agent sessions will be triggered by automations and events, and demonstrates how to build event-driven agentic systems using Devin, starting with Slack as a control plane.

This paper introduces Formal Skill, a runtime-native abstraction for LLM agents that encodes reusable procedures as executable state machines with JSON metadata, Python executors, and hook-governed control logic. An open-source implementation called FairyClaw is presented, showing competitive performance on Harness-Bench with reduced token usage.

Resend Automations enables building event-driven email flows for automated communication.

Google introduces event-driven Webhooks for the Gemini API to reduce latency and friction for long-running jobs like Deep Research and batch processing. This feature replaces inefficient polling with push-based notifications, improving developer experience for agentic applications.