Tagged: architecture
Showing 1–5 of 13 articles
Headlong vs ai-coworkers: What Should an Agent Do When Nothing Is Happening? Laude's Headlong thinks continuously and costs $1-2 an hour at idle. My runtime returns before the model is called. One design question separates them. Read article ai-coworkers: Fusing Six Agent Frameworks and Keeping Their Plugins What I took from OpenClaw, Hermes, ElizaOS, Eve, and the memory papers, what had to be built new, and how existing skills and MCP servers plug straight in. Read article Why No Existing Agent Framework Gives You an AI Coworker I surveyed OpenClaw, NanoClaw, Hermes, ElizaOS, Vercel Eve, and Block's Buzz looking for a long-running coworker with a role. The gap is the same in all six. Read article Orchestration vs choreography: which to choose Side by side comparison of the two saga implementations from the previous posts. What each one cost to build, what it gives you operationally, and which questions to ask before picking. Read article Cloud queue inbox/outbox patterns Building outbox/inbox patterns on DynamoDB Local and LocalStack, with a list of queue smells the patterns don't fully cover. Read article