Prime Agent rewritten in Rust by a 2,000-agent swarm
Prime Intellect shipped a from-scratch Rust rewrite of Prime Agent, its coding agent, which it says has been downloaded more than 300,000 times and processed over 8 trillion tokens since launching in August. Per the company's blog, the port took two weeks and was orchestrated by more than 2,000 agents across 10,000-plus Prime Sandboxes, consuming over 200 billion tokens from Prime Inference's GLM-5.3 endpoint; work was split into a topological ordering of tasks, with each task passing through a Planner, Implementer, Reviewer and Verifier, gated by TUI, harness, protocol and feature parity checks. A follow-up three-day hillclimbing loop logged 144 experiment and audit records and merged 69 changes, cutting cold-start input-ready latency from 736.1 ms in the TypeScript version to 51.9 ms (about 14.18x), 10 MiB session process memory from 1,130.0 MB to 237.3 MB, and install size from 172.1 MB to 59.6 MB.
It is a public, large-scale demonstration of agents rewriting their own codebase, and it raises the bar on speed and resource use for coding-agent harnesses.