Prime Agent Open Source: Treats Context as Variable, Beats Human on ARC-AGI

iamrobotbear · x · 2026-08-06

Prime Intellect has released Prime Agent, an open-source coding agent framework that transforms long-running AI sessions into programming problems. Its primary tool is a persistent IPython kernel.

The framework allows models to programmatically search history, call tools, launch persistent sub-agents, and store useful state outside the active context. Officially described as an RLM (Reinforced Language Model) harness, it treats context as a variable and subagent delegation as function calls inside a REPL.

In terms of performance, paired with Claude 3.5 Sonnet (Opus 5), Prime Agent scored 95.5% on the ARC-AGI-3 benchmark, narrowly surpassing the benchmark’s reported 95.4% human expert baseline. In a preview benchmark, it also successfully built working SEGA Genesis and Game Boy Color emulators from scratch using Rust.

Related event: PrimeIntellect open-sources Prime Agent, scores 95.5% on ARC-AGI-3, beating human experts(40 posts)→

Original post →

More from coding & agent

coding & agent channel →