2026年5月12日·1 分钟阅读

MemPalace — Local-First AI Memory CLI

MemPalace is a local-first memory system with a `mempalace` CLI (+ MCP tools), hitting 96.6% R@5 on LongMemEval with no LLM required.

Anonymous
Anonymous · Community
Agent 就绪

这个资产会安全暂存

这个资产会先安全暂存。复制的指令会要求 Agent 读取暂存文件，并在激活脚本、MCP 配置或全局配置前先确认。

Stage only · 17/100策略：需暂存
Agent 入口
任意 MCP/CLI Agent
类型
CLI Tool
安装
Stage only
信任
信任等级：Community
入口
Asset
安全暂存命令
npx -y tokrepo@latest install ceb88da6-2067-5ba0-93d6-49a073b332fb --target codex

先暂存文件；激活前需要读取暂存 README 和安装计划。

MemPalace is a local-first memory system with a mempalace CLI (+ MCP tools), hitting 96.6% R@5 on LongMemEval with no LLM required.

讨论

登录后参与讨论。
还没有评论，来写第一条吧。

相关资产

LLxprt Code — Multi-Provider AI Coding CLI

LLxprt Code is an open-source AI coding CLI that switches across providers (Anthropic, Gemini, Codex, local). Install via brew or npm.

CLI Tools
Script Depot

mcp2cli — Turn MCP Servers into CLI Tools, Zero Codegen

Convert any MCP server, OpenAPI spec, or GraphQL endpoint into a full CLI at runtime. Saves 96-99% of tokens wasted on tool schemas every turn.

MCP ConfigsCLI Tools
MCP Hub

Unsloth — 2x Faster Local LLM Training & Inference

Unsloth is a unified local interface for running and training AI models. 58.7K+ GitHub stars. 2x faster training with 70% less VRAM across 500+ models including Qwen, DeepSeek, Llama, Gemma. Web UI wi

Skills
AI Open Source

LEANN — Privacy-First RAG with 97% Storage Savings

A local-first retrieval-augmented generation system that runs entirely on personal devices with dramatically reduced storage requirements and no cloud dependency.

Configs
AI Open Source
◈首页🔍搜索👤我的