funes：基于 Lance 的编码智能体本地记忆
原标题：funes: Local Memory for Coding Agents, Built on Lance
AI 摘要
Hugging Face 发布 funes，一个为编码智能体提供本地记忆的工具，基于 Lance 数据集构建。它把 Claude Code、Codex、pi 和 Hermes 的历史会话轨迹索引到一个本地 Lance 数据集中，并提供 recall 和 get 工具让智能体在需要旧上下文时检索原始片段。索引过程完全本地、确定性，不经过 LLM 摘要，并支持凭据脱敏与推送前扫描，强调隐私与可审计性。
正文节选
Your coding agent solved this once. It found the failing test, tried the obvious fix, rejected it, learned the weird constraint, and made a decision. Then the session ended. Next week, a new agent meets the same project as if none of that happened. funes turns those past agent sessions into memory your agents can actually use. It indexes Claude Code, Codex, pi, and Hermes traces into one local Lance dataset, then gives the agent recall and get tools. The next time a task depends on old reasoning