Prime Intellect says 2,000 agents rewrote its coding agent in Rust

Prime Intellect said on October 9th that more than 2,000 agents rewrote Prime Agent, its open-source coding agent, in Rust over more than two weeks, using over 10,000 Prime Sandboxes and more than 200 billion tokens from Prime Inference's GLM-5.3 endpoint. The company reports the Rust version starts faster, uses less memory and adds Windows support, with Prime Agent having been downloaded more than 300,000 times and processed over 8 trillion tokens since its August launch. Prime Intellect says a root agent split the work into dependency-ordered tasks and coordinated planning, implementation, review and verification agents, while separate agents checked the work and engineers directed follow-up fixes after internal testing exposed gaps the scripted parity checks missed.

Prime Intellect says 2,000 agents rewrote its coding agent in Rust The October 9th release pairs the self-rewrite with company-reported startup and memory gains, Windows beta support, and Homebrew installation. By RuntimeWire Staff https://runtimewire.com/author/runtimewire-staff · Published Primary source: Prime Intellect https://www.primeintellect.ai/blog/prime-agent-rust Why it matters The rewrite puts Prime Intellect's own agent and infrastructure through a demanding internal workload. Company benchmarks show lower harness startup latency and memory use, while excluding inference; they do not establish better end-to-end results for customers. Prime Intellect https://www.primeintellect.ai/?ref=runtimewire , co-founded by Vincent Weisser and Johannes Hagemann https://nextomoro.com/johannes-hagemann/?ref=runtimewire , says more than 2,000 agents rewrote Prime Agent, its open-source coding agent, in Rust over more than two weeks, using more than 10,000 Prime Sandboxes and over 200 billion tokens from Prime Inference's GLM-5.3 https://runtimewire.com/models/z-ai/glm-5.3 endpoint. Published on October 9th, the release puts Prime Agent's multi-agent machinery to work on the software itself: Prime Intellect says the Rust version starts faster, uses less memory and adds Windows support https://www.primeintellect.ai/blog/prime-agent-rust?ref=runtimewire . That is a product release and a live demonstration of Prime Intellect's infrastructure thesis. Co-founder Johannes Hagemann https://nextomoro.com/johannes-hagemann/?ref=runtimewire @johannes hage https://x.com/johannes hage?ref=runtimewire and Weisser have built Prime Intellect around giving organizations more control over model training and agent systems. Weisser described that ambition to TechCrunch in July https://techcrunch.com/2026/07/08/prime-intellect-raises-130m-series-a-to-help-enterprises-build-their-own-ai-agents/?ref=runtimewire as broadening access to model training beyond a small group of labs. Hagemann came to the company after work on distributed training at Aleph Alpha, a technical lineage that fits Prime Intellect's infrastructure-heavy focus. The Rust rewrite applies that focus to a coding agent designed for long-running tasks and persistent subagents. A rewrite built around checks Prime Agent launched in August, according to Prime Intellect's release https://www.primeintellect.ai/blog/prime-agent-rust?ref=runtimewire , and the company says it has since been downloaded more than 300,000 times and processed over 8 trillion tokens. Those are company-reported totals; the announcement does not break out active users, retention or how much of that usage was commercial. For the rewrite, Prime Intellect says a root agent divided the work into dependency-ordered tasks and coordinated planning, implementation, review and verification agents. The root agent wrote no product code, Prime Intellect says, so it could focus on task allocation and integration. Separate agents checked the work rather than relying on the same agent to write and approve its own changes. The verification was more concrete than a claim of agent autonomy alone. Prime Intellect compared the Rust and TypeScript versions against scripted tasks, checking rendered terminal frames, session transcripts, requests sent to model providers and daemon-protocol messages. It also had agents audit features component by component. The process reduced the need for human review during the initial port, according to Prime Intellect, but it did not remove people from release decisions: the company says its engineers directed follow-up work, investigated issues found in internal use and reviewed the results. Prime Intellect says internal testing exposed gaps the automated parity checks had not caught. It moved its own agents and staff onto the Rust version, then spent the following weeks fixing bugs, finishing feature work and polishing the interface. Passing scripted parity tests established that selected behaviors matched, not that every real-world workflow was already production-ready. What the speed figures measure Prime Intellect's benchmark https://www.primeintellect.ai/blog/prime-agent-rust?ref=runtimewire compared Rust and TypeScript builds on fresh four-core, 8 GB sandboxes. Its hillclimb table reports cold-start input-ready latency of 51.9 milliseconds for Rust versus 736.1 milliseconds for TypeScript. For large-session process-tree RSS on a 10 MiB session, it reports 237.3 MB for Rust versus 1,130.0 MB for TypeScript. The measurements use a scripted model and exclude inference, so they speak to the agent harness's startup and runtime overhead, not how quickly a model completes an end-to-end coding task. Prime Intellect also compared Prime Agent with other agent harnesses, but its post says there is no common benchmark standard and that those cross-product results should be treated cautiously. The benchmark is useful evidence of a performance change on Prime Intellect's chosen tests; it is not an independent comparison of agents across real customer workloads. Prime Intellect's explanation for moving away from TypeScript centers on Prime Agent's persistent daemon, which streams model output, runs tools and coordinates agents across sessions. The company argues that Rust's native execution and compile-time checks better suit that workload. It also says the rewrite split the code into nine Rust crates and brought Windows support, session crash isolation and a more consistent daemon protocol. Infrastructure becomes the product Prime Intellect's activity visualization separates the Rust port from a performance-optimization phase. The company says the rewrite used more than 2,000 agents and over 200 billion tokens. Prime Intellect says the work ran on two eight-core CPU nodes, while agents sent compilation, type-checking and diffing jobs to Prime Sandboxes. That combination links the agent release to the broader business. Prime Intellect offers compute, inference, sandboxes, training and evaluation tools; using those systems to build and tune Prime Agent gives the company an internal workload as well as a product showcase. The timing follows Prime Intellect's $130 million Series A https://www.primeintellect.ai/blog/series-a?ref=runtimewire , announced in July and led by Radical Ventures, with NVIDIA Ventures, Intel Capital and Dell Technologies Capital among the participants. TechCrunch reported the round at a $1 billion valuation https://techcrunch.com/2026/07/08/prime-intellect-raises-130m-series-a-to-help-enterprises-build-their-own-ai-agents/?ref=runtimewire . Prime Agent remains open source, and the Rust release adds Homebrew installation https://www.primeintellect.ai/blog/prime-agent-rust?ref=runtimewire alongside Windows beta support. The public GitHub repository https://github.com/PrimeIntellect-ai/prime-agent?ref=runtimewire describes it as an agent for coding and long-running autonomous work. The harder commercial test will be whether its reported gains in startup time and memory translate into better outcomes for users, and whether Prime Intellect can turn a self-hosted demonstration of its stack into durable use across its customer base.