🛰️ Daily AI Frontier
‹ back to 2026-08-13

缓存命中率99.93%!DeepSeek最适合的Harness来了,GitHub狂揽8.6万Star

WeChat: 极市平台 LLM Agents 2026-08-11
Representative image for 缓存命中率99.93%!DeepSeek最适合的Harness来了,GitHub狂揽8.6万Star

TL;DR - Open-source coding-agent harness Pi reportedly pairs efficiently with DeepSeek by preserving stable, append-only context, achieving roughly 99.93% cache hits and the lowest successful-task cost in a benchmark of eight harnesses.

  • Pi defaults to four tools—file reading, writing, editing, and command execution—with optional capabilities added through extensions and skills.
  • Native DeepSeek support preserves reasoning content, maps reasoning levels, and fixes session-replay compatibility issues.
  • Composio’s benchmark reported an average cost of about $0.028 per successful task for Pi, versus $0.195 for Claude Code using the same DeepSeek model.
  • DeepSeek is reportedly building an official coding harness to connect its models with terminals, repositories, and developer toolchains.

view merged work →