@irl_danB: everyone is building an agent or a tool you don't want an agent or a tool, you want a reactor I've been working on some…
Summary
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.
View Cached Full Text
Cached at: 06/03/26, 11:56 PM
everyone is building an agent or a tool
you don’t want an agent or a tool, you want a reactor
I’ve been working on something cool and I think you’ll like it
it’s simple: an agent session DAG that keeps a declared world-model up to date in an efficient (memoized) render
each render node is an agent session: you declare the desired state with OpenProse markdown files
once invoked, each agent session acts as the provider. the agent session uses the open source openai-agents-sdk, extensible however you like with any model (I use with opus, sonnet, haiku)
the facets of the world-state are memoized, so not every agent has to run on every event, saving you on inference
if that sounds a lot like React or dataflow, that’s because even in our brave new world the wisdom of the agents holds fast
Similar Articles
@yoheinakajima: my current @activegraphai inspired approach to a modular repo-centric agent operating system
Yohei Nakajima outlines a repo-centric modular architecture for agentic work, where the durable unit is a governed project repository rather than the model or conversation, with agents acting as replaceable execution components over persistent state.
@yoheinakajima: great article, mostly focused on coding agents but applies elsewhere impo. aligns w a lot of my prior thoughts: - agent…
A tweet highlighting key principles for building agent systems, emphasizing scaffolding, memory, and reusable tools, based on an article by Yohei Nakajima.
The agent loop is just ReAct, and your tool-use API already implements it
The article argues that the agent loop is fundamentally the ReAct pattern, and that current tool-use APIs already implement this mechanism.
@DerekNee: everyone is talking about agent loops, harnesses, and self-evolving agents. but almost no one is talking about the actu…
The author argues that a single giant agent is ineffective for running a company, and describes their approach with Matrix, an operating system for autonomous work that organizes agents into a workspace brain, department leads, and scoped workers with proof loops.
I built an agent engine where orchestration lives in a text file, not in code — here's why that matters
The author introduces VITA, a cognitive engine where orchestration is declared in plain-text Markdown files instead of code, enabling dynamic tool loading, no framework lock-in, and provider-agnostic execution.