A lightweight, Git-backed permanent memory for AI agents.
MCPpedia last refreshed this data
io.github.scarletkc/perenna is an MCP server that a lightweight, Git-backed permanent memory for AI agents. Its tool list has not been published yet over stdio, sse and http, requires no API key, and scores 88/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"io-github-scarletkc-perenna": {
"args": [
"perenna"
],
"command": "uvx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
A lightweight, Git-backed permanent memory for AI agents. Claude Code, Codex, ChatGPT, Cursor, and other MCP clients can share durable memories without sharing a vendor account or conversation history.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
uvx 'perenna' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked perenna against OSV.dev.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in ai-ml
MCP client bridge: connects to MCP servers and registers their tools on ctx.tools
An autonomous agent that conducts deep research on any data using any LLM providers
1000+ scientific tools for AI scientists: life science, reserach, literature, and more.
Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.
MCP Security Weekly
Get CVE alerts and security updates for io.github.scarletkc/perenna and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
A lightweight, Git-backed permanent memory for AI agents. Claude Code, Codex, ChatGPT, Cursor, and other MCP clients can share durable memories without sharing a vendor account or conversation history.
Your memory should follow you, not the agent you happen to be using.
Claude Code, Codex, Cursor, and ChatGPT keep memory in separate silos. Switch agents and your memory disappears. Switch machines and local memory stays behind.
Perenna gives them one shared, Git-backed memory. Local agents and ChatGPT can connect to the same self-hosted Perenna service, while every durable memory stays ordinary Markdown you can inspect, edit, version, and back up yourself.
| Perenna | AgentMemory | Mem0 | MemPalace | |
|---|---|---|---|---|
| Simplicity | 3 MCP tools | 54 tools + hooks | SDK/API/server stack | MCP/database stack |
| Local use | stdio, no daemon | Multiple local services | Library or server | Local database |
| Storage | Plain Markdown + Git | Runtime-managed | Database/service-managed | Database-managed |
| Ownership | Your files, your Git history | Runtime-managed | Backend-managed | Backend-managed |
Perenna is small by design: no account, no proprietary memory cloud, no lock-in. Just plain Markdown, Git history, and three focused tools.
Paste this into Claude Code, Codex, ChatGPT Desktop, Cursor, or another coding agent with terminal and local MCP configuration access:
Open the following URL, read the complete instructions, and follow them to
install and connect Perenna:
https://raw.githubusercontent.com/scarletkc/Perenna/main/docs/guides/agent-installation.md
Perenna requires Python 3.12+, Git, and uv.
uv tool install perenna
Install the optional memory behavior skill for the local client:
perenna skill install --agent codex
# or
perenna skill install --agent claude-code
Repeat --agent in one command when both clients should receive the skill.
The [configuration reference](https://github.com/scarletkc/Perenna/blob/main/docs/reference/configuration.md#bundled