Clip / AI Agents

Simplest experiment: hand the coding agent an RLM as a tool

From Recursive Coding Agents - Raymond Weitekamp, OpenProse · ≈11:23

The lowest-effort way to get RLM behavior today — wrap an RLM package as a CLI so the agent can delegate a 100-million-token corpus sift to it instead of loading anything into its own context.

What’s in it

The lowest-effort way to get RLM behavior today — wrap an RLM package as a CLI so the agent can delegate a 100-million-token corpus sift to it instead of loading anything into its own context.

Watch this moment ↗

Clip transcript

the October RLM blog post came out in 2025. Okay, so I'll show some of my experiments on recursive coding agents. The first one was simply wrapping Alex's RLM package as a CLI. So, the idea was I just want to give my coding agent an RLM as a tool call. So, let's say we go we need to go sift through a 100 million token corpus. Uh well, now I just use this that tool and then the RLM does the RLM thing. So, that's interesting. And it can be very useful. Uh and a few other people have built uh things like that.

Intel