Signal Garden

开发者工具DEVELOPER TOOLS· CLI

memory.cpp

KirtiRamchandani/memory.cpp

给AI编程助手装上本地记忆,记住项目规则和上下文。A local-first memory system for coding agents that compresses context and remembers what matters.

根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.

适用平台Platforms
claude-code
已识别的要求Documented requirements
Local runtime
许可LICENSE
MIT

每周一 1 封:本周热度最高的 10 个 GitHub 新项目。免费,随时退订。One email each Monday: the 10 hottest new GitHub projects this week. Free, unsubscribe any time.

订阅即表示你同意我们按隐私政策发送每周一周刊。我们会记录这次订阅的来源页面和活动标签,这条记录不包含 IP 地址。Subscribing means you agree that we email the Monday weekly digest as described in the privacy policy. We record the referring page and campaign tag for the signup, and that record does not include an IP address. 隐私政策Privacy Policy

Featured on Signal Garden
徽章主题Badge theme

能力CAPABILITIES

它能帮你做成什么What it helps you do

  1. 01

    记住项目关键约定和决策

  2. 02

    把上下文压缩成可缓存的小包

  3. 03

    检查缓存内容是否完整

  4. 04

    生成可复现的上下文锁文件

  5. 05

    一键输出项目记忆报告

  1. 01

    Store durable facts about your project with tags.

  2. 02

    Compile relevant context into a cache-stable pack.

  3. 03

    Inspect typed memory blocks with source anchors and freshness.

  4. 04

    Generate a reproducible lockfile and provenance ledger.

  5. 05

    Block stale, contradictory, or secret content automatically.

上手GET STARTED

怎么装How to install

Cargo · Rust
cargo install --path crates/memory-cli

选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.

打开项目文档Open project documentation ↗

使用限制LIMITATIONS

限制与风险Limits and risk

以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.

限制LIMITS

未知Unknown

01需要 API KeyREQUIRES API KEY
未在文档中发现Not found in the docs
02需要本地环境NEEDS LOCAL RUNTIME
是Yes
03需要 DockerNEEDS DOCKER
未在文档中发现Not found in the docs
04难度DIFFICULTY
需要开发经验Needs development work
05许可LICENSE
MITMIT
06阶段STAGE
持续活跃Active
创建于 18 MAY 2026Created 18 MAY 2026

静态扫描STATIC SCAN

在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.

静态扫描未发现明显风险,但不代表安全The static scan found no obvious risk patterns in the documentation, but this does not prove the software is safe.

项目动态PROJECT ACTIVITY

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

09 NOV 202609 NOV 2026

增长GROWTH

+53.2%+53.2%

432 → 662 stars · 12 个快照432 → 662 stars · 12 snapshots

状态STATUS

持续活跃Active

质量 AQuality A

Compresses raw context from 84,000 tokens to 1,420 tokens (98% reduction).

每周一周刊Monday weekly digest

每周一 1 封:本周热度最高的 10 个 GitHub 新项目。免费,随时退订。One email each Monday: the 10 hottest new GitHub projects this week. Free, unsubscribe any time.

看第 1 期Read issue 1

订阅即表示你同意我们按隐私政策发送每周一周刊。我们会记录这次订阅的来源页面和活动标签,这条记录不包含 IP 地址。Subscribing means you agree that we email the Monday weekly digest as described in the privacy policy. We record the referring page and campaign tag for the signup, and that record does not include an IP address. 隐私政策Privacy Policy

订阅每周一周刊Subscribe to the Monday weekly digest
PROVENANCE · 这些结论的依据是什么Where these conclusions come from
来源 URLSource URL
https://github.com/KirtiRamchandani/memory.cpp
原始数据哈希Raw data hash
3706d8230f5e827c9398676f2a9d7e73
解析时间Parsed at
2026-11-10T23:59:50.042Z
最后一次验证Last verified
2026-11-20T22:14:42.723Z
增长测量时间Growth measured
2026-11-11T00:10:11.922Z
发现查询Discovery queries
focus:token:repo:topic-context-engineering
分类来源Category source
rules
焦点Focus
token (8)
完整解析证据 JSONFull parse evidence JSON
{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "tree: .claude/"
    }
  ],
  "apiKey": null,
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 7,
      "dev-tools": 10,
      "indie-web": 0,
      "skill-agent": 6,
      "productivity": 3
    },
    "primary": "dev-tools",
    "secondary": "cli"
  },
  "localRuntime": "prefix-cache benefit against vLLM / llama.cpp / Ollama / SGLang, run [`sc",
  "skillMdTotal": 0,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 1,
    "agent": 0,
    "media": 0,
    "design": 0,
    "browser": 0,
    "devtool": 8,
    "security": 2,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "description mentions AI",
      "weight": 0.2
    }
  ],
  "scannedSources": [
    "readme"
  ],
  "skillMdFetched": 0
}