HomeBlogPricingCareersDocsGitHubSlack community
Field notes/Community builds/I Forked One AI Agent Into 12 Workers — and Every Clone Woke Up Already Knowing Everything

I Forked One AI Agent Into 12 Workers — and Every Clone Woke Up Already Knowing Everything

Cold-starting a worker costs 11 to 14 seconds of setup tax. Snapshot the parent once and each of 12 forks lands in about 2.4 seconds, with the isolation checked by deleting files inside one of them.

SBX-01C4SBX-01E3SBX-0202SBX-0221SBX-0240SBX-025FSBX-027ESBX-029DSBX-02BCSBX-02DBSBX-02FASBX-0319SBX-0338SBX-0357SBX-0376[ RUNTIME: ACTIVE ] P50 2.45S · P99 4.12S · 5M/PROJECT

Chew's second build on this page, and the first one to put numbers on snapshot-and-fork. The agent is deliberately small: read a buggy Python file, ask DeepSeek to fix it, run assertions on what comes back. The measurement is the point. A cold sandbox plus dependencies plus agent code costs 11 to 14 seconds per worker, so a 12-worker fleet pays roughly 147 seconds before any of them does useful work. Snapshotting the parent once takes 15.8 seconds, each fork after that lands in about 2.4 seconds, and the same fleet comes up in around 45 seconds. He then deletes files inside one fork to confirm the other eleven never see it.

Read it for the caveats as well. He hit a concurrency ceiling lower than the free tier advertised and a file write to a root-level path that failed, which we have since fixed in the docs. His own conclusion is the honest one: forking earns its keep for batch evaluation and RL rollouts, and not for a single long-lived agent.

We didn’t write this one — it’s Chew Loong Nian’s piece, published on Towards AI. The note above is ours; the full article is theirs.

Read the full piece on Towards AI
CN
WRITTEN BYChew Loong NianCommunity · Towards AI
Read next —FROM THE LOG
◆ THE SANDBOX DIGEST

Subscribe for release notes, benchmarks, deep dives.

One dispatch per month from the Tensorlake team — no spam.