MCP Servers · Memory

chinwe/compound-memory

Name: chinwe/compound-memory
Author: Various

Local multi-agent shared memory with compounding — MCP server + CLI

Visit site ↗

Our verdict

Not reviewed yet

We have not reviewed chinwe/compound-memory yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About chinwe/compound-memory

A local multi-agent shared memory system with compounding capabilities, provided as an MCP server and CLI. It enables agents to store and retrieve memory that builds on prior knowledge, facilitating persistent context across sessions.

Best for

Developers experimenting with multi-agent memory systems in local, Python-based setups.

Use cases

Persist and share context between multiple AI agents
Build cumulative knowledge bases for agent workflows
Integrate memory into MCP-compatible tools

Notes

1 stars on GitHub. Last updated 2026-10-22. Licensed MIT.

Pros

Local-first, keeping data on your own infrastructure
Provides both MCP server and CLI for flexible integration
Supports compounding memory, allowing knowledge to grow over time

Cons

Very early stage with only 1 star, likely unstable
Limited documentation and community support
Python-only, requiring a Python environment

Key facts

What we have checked

Not checked yet. Dated facts such as prices, releases and repository activity appear here once we have confirmed them from a source.

Install

Add chinwe/compound-memory to your client

Not verified yet

Our lab has not run this server yet. "Config checked" on a client means the recipe matches that client's documented config format; it does not mean we ran it.

Claude Code

Config checked

Run in your terminal (runs on your computer)

claude mcp add --transport stdio chinwe-compound-memory -- uvx compound-memory@0.5.10

Version 0.5.10 · From the Official MCP registry, read 24 Oct 2026 · Format checked against Claude Code's config docs

Claude Desktop

Config checked

Add to claude_desktop_config.json (runs on your computer)

{
  "mcpServers": {
    "chinwe-compound-memory": {
      "command": "uvx",
      "args": [
        "compound-memory@0.5.10"
      ]
    }
  }
}

Version 0.5.10 · From the Official MCP registry, read 24 Oct 2026 · Format checked against Claude Desktop's config docs

Cursor

Config checked

Add to .cursor/mcp.json (runs on your computer)

{
  "mcpServers": {
    "chinwe-compound-memory": {
      "command": "uvx",
      "args": [
        "compound-memory@0.5.10"
      ]
    }
  }
}

Version 0.5.10 · From the Official MCP registry, read 24 Oct 2026 · Format checked against Cursor's config docs

VS Code

Config checked

Add to .vscode/mcp.json (runs on your computer)

{
  "servers": {
    "chinwe-compound-memory": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "compound-memory@0.5.10"
      ]
    }
  }
}

Version 0.5.10 · From the Official MCP registry, read 24 Oct 2026 · Format checked against VS Code's config docs

Codex

Config checked

Add to ~/.codex/config.toml (runs on your computer)

[mcp_servers.chinwe-compound-memory]
command = "uvx"
args = ["compound-memory@0.5.10"]

Version 0.5.10 · From the Official MCP registry, read 24 Oct 2026 · Format checked against Codex's config docs

ChatGPT: ChatGPT connects only to remote servers that need no API key.

Recipes come from the server's entry in the official MCP registry. Check the package name before you run it, and keep keys out of shared files.

Works with

What chinwe/compound-memory connects to

5 clients, each with how we know and when we checked.

Works with	Type	How we know	Checked
Claude Code	Client	Install recipe matches the client's documented formatRuns locally, version 0.5.10Config checked	24 Oct 2026Claude Code docs
Claude Desktop	Client	Install recipe matches the client's documented formatRuns locally, version 0.5.10Config checked	24 Oct 2026Claude Desktop docs
Cursor	Client	Install recipe matches the client's documented formatRuns locally, version 0.5.10Config checked	24 Oct 2026Cursor docs
VS Code	Client	Install recipe matches the client's documented formatRuns locally, version 0.5.10Config checked	24 Oct 2026VS Code docs
Codex	Client	Install recipe matches the client's documented formatRuns locally, version 0.5.10Config checked	24 Oct 2026Codex docs

Sources

Where this comes from

No sources recorded yet. Each source we check is listed here with the date we checked it.

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

Pairs with

Other entries in the index that connect to this one. Click through to see the chain.

Pairs with2 entries

MMCPMemorylowCatalogue

topoteretes/cognee

Various

Memory platform for AI Agents in 6 lines of code

★ 17,624

MMCPMemorylowCatalogue

vectorize-io/hindsight

Various

Hindsight: Agent Memory That Learns

★ 15,407

Works in3 entries

AAgentslowCatalogue

Crewai

Community

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

★ 55,300

AAgentslowCatalogue