# robocoop-3: Agentic Runtime Function.

**URL:** <https://talk.observablehq.com/t/robocoop-3-agentic-runtime-function/10583>\
**Category:** Show and tell\
**Created:** [January 31, 2026, 8:00pm UTC](https://talk.observablehq.com/t/robocoop-3-agentic-runtime-function/10583 "2026-01-31T20:00:32Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![tomlarkworthy](https://yyz2.discourse-cdn.com/flex030/user_avatar/talk.observablehq.com/tomlarkworthy/32/5940_2.png) [@tomlarkworthy](https://talk.observablehq.com/u/tomlarkworthy)\
**Post date:** [January 31, 2026, 8:00pm UTC](https://talk.observablehq.com/t/robocoop-3-agentic-runtime-function/10583/1 "2026-01-31T20:00:32Z")

</div>

robocoop-3 is my new assistant! Its awesome!

> **[robocoop3: agents-as-functions](https://observablehq.com/@tomlarkworthy/robocoop-3)**
>
> Calling \`viewof agent = robocoop3({...})\` creates a prompting UI and an in-notebook agent whose responses are streamed to the value of \`agent\`. You can create many such agents at-once. The function is essentially the agentic loop expressed as a...

This put the Agentic loop inside a generator function, it works quite differently to robocoop-2. It doesn’t know Observable 1.0 syntax, instead, it directly reads and writes the runtime. It is amazing investigating and finding bugs, if you prod it a bit. It can hold a multi-turn dialogue, and can use Anthropic, OpenAI or Ollama (local models!).

I still use robocoop-2 to write notebooks, because that can read and write Observable 1.0 syntax. robocoop3 is much snappier to use though, because it properly does streaming and parallel tool calls. robocoop-3 was made by porting Opencode, and iterated on with robocoop-2.

I see robocoop-3 as a building block for other workflows, e.g. Wiggam Loop, AI-as-judge etc. More of a thing you will instanciate a few times in a few different places and customize to the situation. I have not tuned its prompt very much yet, that will be next, but as I am finding it useful fixing a few long running bugs, I thought I would share it now, as I am not gonna work on it for a little while, its good enough for now, especially when combined with robocoop-2.

robocoop-3 was powerful enough to write its own integration with moltbook! [moltbook - the front page of the agent internet](https://www.moltbook.com/u/robocoop3)

Oh I also wired up a demo provider which is a bit slower than direct API calls because it goes through a proxy, but you can try it out now for FREE. BUT, you are limited to openAPI GPT 5-mini (cheap!). Put your own key to get the faster and most intelligent gpt 5.2 experience.