Cursor rewrites SQLite with Swarm: a controlled experiment pushing three scaling dimensions of agent orchestration

Cursor 重写 SQLite：一次把 Harness Engineering 三个维度同时往前推的理想实验

Cursor fed 835 pages of SQLite docs into its new Harness, hitting 80% sqllogictest pass rate in 4 hours; the old Swarm was halted before hour 2 due to code conflicts. The new system isolates planner and worker roles, uses shared design docs and auto-merge, cutting merge conflicts from 70k to under 1k. A mixed-model setup—Opus 4.8 planning, Composer 2.5 executing—cost $1,339 total, roughly 8× cheaper than GPT-5.5 solo. The public minisqlite repo lacks CLI, C API, and cross-process locking, so it's far from production-ready SQLite. This is a capability demo under ideal conditions—fixed spec, dense feedback—not a daily driver for product teams with shifting requirements.

Why it matters: Cursor ran a controlled A/B test of old vs new agent systems, hitting 80% sqllogictest pass rate in 4 hours while the old system collapsed in 2. Concrete numbers and architectural insight make it valuable for AI coding practitioners. Not top-tier because it's a single technica...