Tag
CachyLLama is a fork of llama.cpp that adds a persistent SSD-backed KV cache and multi-tier caching, dramatically reducing prompt reprocessing time for long local-agent sessions on slower hardware.
A developer introduces a concept called a 'reactor' — an agent session DAG that maintains a memoized world-model using OpenProse markdown files and the openai-agents-sdk, drawing parallels to React and dataflow.
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.