What a Coding Agent Costs

An open-source benchmark by smelt developer Leonard Cser measured CPU and memory use across seven coding agents and found memory consumption differs by up to 74x, with opencode taking 430 MiB directly after startup versus 5.8 MiB for fx and 19 MiB for smelt 0.8.0. The benchmark, run on a single Ryzen 9 7900X machine with each agent given an identical scripted model in a fresh 2-CPU container and sampled every 100 ms, also found terminal UI rendering can consume as much CPU as the task itself — claude code rose from 3% to 43% of one core and opencode from 4% to 48% as model speed went from 30 to 1,000 tokens per second. Cser reported that smelt's engine used the least CPU at 0.12 s but its TUI added 1.5 s, 13 times more, putting smelt above pi (1.4 s) overall.

What a coding agent costs your machine I’m working on an open-source coding agent called smelt. I want it to be fast and lean, with all the features of the other agents. I’m biased, so I needed an honest way to check my progress. I wrote a benchmark https://leonardcser.github.io/harness-resource-bench that captures the cost of running an agent. I ran it on , https://claude.com/product/claude-code codex https://developers.openai.com/codex , , https://fx.sh omp https://omp.sh , , https://opencode.ai pi https://pi.dev and . Here are the best results, including where smelt falls short. https://github.com/leonardcser/smelt Takeaways 1. Memory use differs by up to 74x between agents. 2. The TUI adds as much CPU as the work itself. 3. smelt has the cheapest engine, but the TUI adds 13 times more CPU. How I measured 1. All agents get the same scripted model, so their replies and tool calls are identical. 2. Each run uses a new container with 2 CPUs. 3. CPU and memory are read every 100 ms, from outside the container. 4. Each case runs 3 times. The charts show the median, and the whiskers are the lowest and highest run. The benchmark is open source https://github.com/leonardcser/harness-resource-bench and I ran the following versions: claude code 2.1.319, codex 0.167.0, fx 0.0.16, omp 18.18.0, opencode 2.2.6, pi 1.5.0 and smelt 0.8.0. Newer versions may differ. Memory varies 74x opencode takes 430 MiB directly after starting. fx takes 5.8 MiB. smelt takes 19 MiB. The TUI costs as much as the task Drawing onto the terminal costs as much CPU as the task itself or more. codex, omp and opencode are exceptions. A faster model makes it worse. From 30 to 1,000 tokens per second, claude code goes from 3% to 43% of one core, opencode from 4% to 48%. Where smelt falls short The smelt engine uses the least CPU. 0.12 s is spent on the task. The TUI adds 1.5 s to it. That’s 13 times more. With the TUI, smelt uses more CPU than pi 1.4 s . The UI is where smelt can improve most. Limits I wrote the benchmark as well as smelt, and I built smelt with these numbers in front of me. It’s a scripted model, so none of this gives us any idea of the quality of answers. It all ran on one Ryzen 9 7900X machine. The specifics of each agent’s setup are in the repo. The full results https://leonardcser.github.io/harness-resource-bench have every chart, including idle CPU, startup and long sessions. A note: I put real thought into these posts. Every word here comes from the human me. Thanks for reading.