MCP Servers · Memory
hjqcan/GoodMemory
Local-first, auditable memory layer for AI apps and coding agents — Codex, Claude Code, MCP, HTTP, TypeScript, and Python.
Our verdict
We have not reviewed hjqcan/GoodMemory 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.
From the listing
About hjqcan/GoodMemory
GoodMemory is a local-first, auditable memory layer for AI applications and coding agents. It integrates with Codex, Claude Code, MCP, HTTP, TypeScript, and Python, allowing agents to store and retrieve memory while keeping data on local infrastructure.
Best for
Developers building AI agents that need persistent, auditable memory.
Use cases
- Give coding agents persistent memory across sessions
- Expose agent memory to tools via MCP or HTTP
- Audit memory reads and writes in AI workflows
Notes
17 stars on GitHub. Last updated 2026-08-22. Licensed MIT.
Pros
- Local-first design keeps data on your own infrastructure
- Auditable memory supports transparency and debugging
- Works with multiple agent ecosystems and protocols
Cons
- Very early-stage project with few stars and limited adoption
- No single vendor backing, so support is community-driven
- Requires self-hosting and setup for each environment
Key facts
What we have checked
- Days since the last commit
- 28
- GitHub forks
- 2
- GitHub stars
- 21
- Days to a first reply on issues
- 80.1
- Open issues
- 2
- Releases in the last 90 days
- 4
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
How to use
How to set it up
As the listing publishes it. We have not run this install.
Install
npm install -g goodmemory@0.8.3Clients the listing names (not checked here)
Claude Desktop, Claude Code, Cursor, Windsurf, Cline, ChatGPT
Install
Add hjqcan/GoodMemory to your client
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 checkedRun in your terminal (runs on your computer)
claude mcp add --transport stdio hjqcan-goodmemory -- npx -y goodmemory@0.7.5 mcp serve --user-id YOUR_USER_IDClaude Desktop
Config checkedAdd to claude_desktop_config.json (runs on your computer)
{
"mcpServers": {
"hjqcan-goodmemory": {
"command": "npx",
"args": [
"-y",
"goodmemory@0.7.5",
"mcp",
"serve",
"--user-id",
"YOUR_USER_ID"
]
}
}
}Cursor
Config checkedAdd to .cursor/mcp.json (runs on your computer)
{
"mcpServers": {
"hjqcan-goodmemory": {
"command": "npx",
"args": [
"-y",
"goodmemory@0.7.5",
"mcp",
"serve",
"--user-id",
"YOUR_USER_ID"
]
}
}
}VS Code
Config checkedAdd to .vscode/mcp.json (runs on your computer)
{
"servers": {
"hjqcan-goodmemory": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"goodmemory@0.7.5",
"mcp",
"serve",
"--user-id",
"YOUR_USER_ID"
]
}
}
}Codex
Config checkedAdd to ~/.codex/config.toml (runs on your computer)
[mcp_servers.hjqcan-goodmemory]
command = "npx"
args = ["-y", "goodmemory@0.7.5", "mcp", "serve", "--user-id", "YOUR_USER_ID"]- 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 hjqcan/GoodMemory 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 0.7.5Config checked | Claude Code docs |
| Claude Desktop | Client | Install recipe matches the client's documented formatRuns locally, version 0.7.5Config checked | Claude Desktop docs |
| Cursor | Client | Install recipe matches the client's documented formatRuns locally, version 0.7.5Config checked | Cursor docs |
| VS Code | Client | Install recipe matches the client's documented formatRuns locally, version 0.7.5Config checked | VS Code docs |
| Codex | Client | Install recipe matches the client's documented formatRuns locally, version 0.7.5Config checked | Codex docs |
Stars and usage
How hjqcan/GoodMemory is growing
20 to 21
Health and security
Is hjqcan/GoodMemory looked after, and what do its setup files show
Health score
56 out of 100
| Part | Points | What we saw |
|---|---|---|
| Recent activity | 30 of 30 | Last push 28 days ago |
| Releases | 15 of 15 | 4 releases in 90 days |
| Issue replies | Not counted | The latest check has no issue response reading (fewer than 3 measured issues, or issues switched off) |
| Maintainer | 0 of 15 | Owned by a single user |
| Official source | 0 of 20 | Community server |
Security check static checks
100 out of 100
- Note The lab has not recorded this server's tool list yet, so tool permissions were not checked.
Alternatives
Alternatives to hjqcan/GoodMemory
| Record | Type | How we know | Checked |
|---|---|---|---|
| topoteretes/cogneeThis is an alternative to it | MCP server | Named in the listing | Not dated |
| vectorize-io/hindsightThis is an alternative to it | MCP server | Named in the listing | Not dated |
Compare
Compare hjqcan/GoodMemory side by side
Sources
Where this comes from
- GitHubRegistry
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.
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.