C
chinwe/compound-memory
Local multi-agent shared memory with compounding — MCP server + CLI
无 SECURITY.md
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
- 复制上面的命令
- 粘成
claude_desktop_config.json里mcpServers的一项（本地服务器用 command + args，示例见 客户端接法） - 重启客户端
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"chinwe-compound-memory": {
"command": "uvx",
"args": ["--from", "compound-memory", "compound-memory-server"]
}
}
}解析自我们于 2026-10-26 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"chinwe-compound-memory": {
"command": "uvx",
"args": ["--from", "compound-memory", "compound-memory-server"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio chinwe-compound-memory -- uvx --from compound-memory compound-memory-server
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- ★ 数取值
- 1 ★ · chinwe/compound-memory · 取自 GitHub 搜索 API · （2026-11-13 20:00:50 核对）
- 来源明细
- 收录自 punkpeye/awesome-mcp-servers 榜单（我们从中收集的条目之一） · 条目类型：MCP 服务
- 收录与活跃
- 收录于 2026-10-23 · 最近见到 2026-11-14 · 共见到 26 次 · 被 23 个来源列出
- 评分构成
- 综合分 2,300 · 1 ★ · 23 个来源 · mcp
- 安装
uvx --from compound-memory compound-memory-server
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
uvx --from compound-memory compound-memory-server。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: MCP 服务。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
仓库
chinwe/compound-memory；我们收录于 2026-10-23；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。# compound-memory
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
English | 简体中文
Local-first shared memory for multiple AI agents — plain Markdown files that compound in value as they are used. Memory lives on your disk as frontmatter-annotated Markdown, gets stronger with every confirmed use, decays into a revivable archive when neglected, and auto-commits to a local git history on every write.
## Why
Every agent session starts from zero: preferences get re-asked, project conventions get re-discovered, the same pitfall gets hit twice. compound-memory gives all your agents one shared store:
Local-first — nothing leaves your machine; memories are human-readable Markdown files, not rows in an opaque database.
MCP-native — exactly 5 tools (memorywrite / memorysearch / memoryget / memorylink / memoryfeedback) as the single read-write boundary; works with any MCP host (Claude Code, ZCode, WorkBuddy, …), plus a full CLI for operations.
Compounding — confirmed usage raises confidence, related memories are recalled as neighbors, validation from a different host counts as independent evidence, and distillation merges many raw memories into fewer, denser ones.
Multi-agent by design — a shared namespace everyone reads, plus agent- private namespaces each host owns; cross-host validation is tracked per host.
Optional semantic recall — vector search via sqlite-vec + BGE embeddings, with automatic graceful fallback to pure lexical search when unavailable. Override the model with COMPOUNDMEMORYEMBEDDINGMODEL (default Xenova/bge-small-zh-v1.5) and COMPOUNDMEMORYEMBEDDINGDIM (default 512); changing either is an ops action and needs an explicit rebuild-index.
## Quick Start
### For AI agents
Paste this one-liner into your coding agent (Claude Code, Cursor, ZCode, …) and let it do the rest:
text
Set up compound-memory (https://github.com/chinwe/compound-memory) — a local-first multi-agent shared memory (MCP server + CLI) — on this machine. Do not clone the repo for a normal install. Initialize the store with uvx --from compound-memory compound-memory init (defaults to ~/.agents/memory). Register its stdio MCP server in this host's MCP config: command uvx, args --from compound-memory compound-memory-server, env COMPOUNDMEMORYROOT=$HOME/.agents/memory and COMPOUNDMEMORYAGENTID=agent- . Verify by calling memorysearch and expecting a {"hits": [...]} response; if the host needs a restart to load MCP servers, tell me. Use uv run --directory only when developing against a local checkout. Short English setup and the search → feedback → write loop: docs/agent-integration.en.md. Full per-host configs: docs/agent-integration.md.
### For humans
#### 1. Install
Python ≥ 3.11. The default does not clone the repo:
bash
# Default: PyPI. Hosts launch the MCP server with
# uvx --from compound-memory compound-memory-server
# Optional CLI on PATH:
uv tool install compound-memory # or: pip install compound-memory
# Developer / local checkout only — not the default host launch
git clone https://github.com/chinwe/compound-memory.git
cd compound-memory && uv sync --extra dev
#### 2. Initialize your store
Defaults to ~/.agents/memory; override with the COMPOUNDMEMORYROOT env var. A leading ~ or $HOME is expanded; a blank override falls back to the default.
Local-first shared memory for multiple AI agents — plain Markdown files that compound in value as they are used. Memory lives on your disk as frontmatter-annotated Markdown, gets stronger with every confirmed use, decays into a revivable archive when neglected, and auto-commits to a local git history on every write.
## Why
Every agent session starts from zero: preferences get re-asked, project conventions get re-discovered, the same pitfall gets hit twice. compound-memory gives all your agents one shared store:
Local-first — nothing leaves your machine; memories are human-readable Markdown files, not rows in an opaque database.
MCP-native — exactly 5 tools (memorywrite / memorysearch / memoryget / memorylink / memoryfeedback) as the single read-write boundary; works with any MCP host (Claude Code, ZCode, WorkBuddy, …), plus a full CLI for operations.
Compounding — confirmed usage raises confidence, related memories are recalled as neighbors, validation from a different host counts as independent evidence, and distillation merges many raw memories into fewer, denser ones.
Multi-agent by design — a shared namespace everyone reads, plus agent- private namespaces each host owns; cross-host validation is tracked per host.
Optional semantic recall — vector search via sqlite-vec + BGE embeddings, with automatic graceful fallback to pure lexical search when unavailable. Override the model with COMPOUNDMEMORYEMBEDDINGMODEL (default Xenova/bge-small-zh-v1.5) and COMPOUNDMEMORYEMBEDDINGDIM (default 512); changing either is an ops action and needs an explicit rebuild-index.
## Quick Start
### For AI agents
Paste this one-liner into your coding agent (Claude Code, Cursor, ZCode, …) and let it do the rest:
text
Set up compound-memory (https://github.com/chinwe/compound-memory) — a local-first multi-agent shared memory (MCP server + CLI) — on this machine. Do not clone the repo for a normal install. Initialize the store with uvx --from compound-memory compound-memory init (defaults to ~/.agents/memory). Register its stdio MCP server in this host's MCP config: command uvx, args --from compound-memory compound-memory-server, env COMPOUNDMEMORYROOT=$HOME/.agents/memory and COMPOUNDMEMORYAGENTID=agent- . Verify by calling memorysearch and expecting a {"hits": [...]} response; if the host needs a restart to load MCP servers, tell me. Use uv run --directory only when developing against a local checkout. Short English setup and the search → feedback → write loop: docs/agent-integration.en.md. Full per-host configs: docs/agent-integration.md.
### For humans
#### 1. Install
Python ≥ 3.11. The default does not clone the repo:
bash
# Default: PyPI. Hosts launch the MCP server with
# uvx --from compound-memory compound-memory-server
# Optional CLI on PATH:
uv tool install compound-memory # or: pip install compound-memory
# Developer / local checkout only — not the default host launch
git clone https://github.com/chinwe/compound-memory.git
cd compound-memory && uv sync --extra dev
#### 2. Initialize your store
Defaults to ~/.agents/memory; override with the COMPOUNDMEMORYROOT env var. A leading ~ or $HOME is expanded; a blank override falls back to the default.
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/chinwe-compound-memory/)
- 来源
- awesome · https://github.com/chinwe/compound-memory
- 按领域浏览
- MCP 服务
- Traction
- 1 ★
- 收录来源
- 23 个独立来源
- 收录于
- 今天
- 安全策略
- 我们没在该仓库根目录找到
SECURITY.md（这不代表不安全）
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。