Agent hillclimbs SDK to 33% smaller bundles and 16x less memory over 123 commits
samgoodwin89 · x · 2026-10-30
Alchemy pointed an agent at distilled, their Effect-native SDKs covering 88 cloud providers, with one job: make every benchmark number go down. Over 123 commits and 84 benchmark runs it kept what helped and dropped what didn't.
Results (medians over 98 programs):
- Bundle per call: 57.1 → 38.3 KB gzip (-33%)
- Added latency per call: 19.5 → 4.0 µs (-79%)
- Import memory: 2.15 → 0.57 MB (-74%)
- Importing all of AWS: 227 → 13.9 MB (16x)
Vs official SDKs on the same calls, distilled is 2.2–6x smaller, up to 108x lower call latency, and 1.2–3x faster cold start. A showcase of hillclimbing-style agent-driven performance optimization.
Related event: Alchemy Agent Optimizes SDK, Claims Big Wins Over Official SDKs(3 posts)→
More from coding & agent
- Repo-native tooling: a sandboxed agent workflow using Git as a dead drop — OutrageousAbies5835 · 2026-10-30
- Anthropic engineer shows agent engineering shifting from prompts to self-improving systems — goyalshaliniuk · 2026-10-30
- The agent harness isn't for the agent — it's for us — seanmcdonaldxyz · 2026-10-30
- YC F26's Composal sends agent swarms to test your product like real users — ycombinator · 2026-10-30
- KreaMossMix ComfyUI workflow chains MOSS-Image and Krea 2 for four image variants per prompt — Plane-Implement1044 · 2026-10-30
- Dev builds fail-closed MCP tool that refuses to PASS unverified US businesses — cstill_dev · 2026-10-30