Perenna

io.github.scarletkcPublished by GitHub account scarletkcv0.4.1Updated Oct 24, 2026

A lightweight, Git-backed permanent memory for AI agents.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Perenna is a local, Git-backed permanent memory server that lets AI assistants read, write and delete durable memories shared across MCP clients.

What you can do
Read, write and delete durable memories through separate MCP tools, stored as human-readable Markdown in an independent Git repository. Share one memory store across Claude Code, Codex, Cursor, ChatGPT and other MCP clients instead of separate vendor silos. Search memories through a local Vexor retrieval index that can be rebuilt from Git. Optionally import, publish or fast-forward memory history through a private Git repository. Run multiple local agent processes against the same store with cross-process locking.
When to use it
Useful when you switch between several AI agents or machines and want one durable memory that follows you rather than staying locked in one vendor's account. Also suited to users who want their agent memory to remain inspectable, editable and versionable Markdown they control.
Requirements
Runs locally over stdio as a Python package (Python 3.12+, Git and uv). Needs a working Vexor embedding provider, configured interactively or via VEXOR_CONFIG_JSON plus VEXOR_API_KEY or the provider's key; local embeddings need the local extra. Optional Git sync needs a private repository and PERENNA_GIT_REMOTE. Data is created under ~/.perenna/ by default.
Before you install
Remote embedding or reranking providers receive memory text and search queries, so memory content leaves the machine. VEXOR_API_KEY and VEXOR_REMOTE_RERANK_API_KEY are secrets; keep them in the host environment. The server can write and delete memories, and Git sync publishes memory history to a remote repository, so use a private one.

Installation

In SourceWeft

  1. Open Perenna in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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.

  • Separate MCP tools for reading, writing, and deleting memories
  • Local stdio, loopback-only Streamable HTTP, and OAuth-protected remote HTTP
  • Human-readable Markdown stored in an independent Git repository
  • Local Vexor retrieval index that can always be rebuilt from Git
  • Cross-process locking for multiple local agent processes

Why Perenna?

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 stays focused on permanent memory: no required account, proprietary memory cloud, or automatic conversation extraction.

Quickstart

Install with your AI agent

Paste this into Claude Code, Codex, ChatGPT Desktop, Cursor, or another coding agent with terminal and local MCP configuration access:

text
Open the following URL, read the complete instructions, and follow them toinstall and connect Perenna:https://raw.githubusercontent.com/scarletkc/Perenna/main/docs/guides/agent-installation.md

Install a published release

Perenna requires Python 3.12+, Git, and uv.

Install Perenna
bash
uv tool install perenna
Configure retrieval

Perenna needs a working Vexor embedding provider. For interactive provider selection and configuration, run:

bash
uvx vexor init

Perenna automatically reuses ~/.vexor/config.json. When using process-level configuration, make sure the MCP server receives VEXOR_CONFIG_JSON plus VEXOR_API_KEY or the selected provider's key from its host environment. Remote providers receive memory text and search queries.

If you choose local embeddings, also install Perenna's local extra:

bash
uv tool install "perenna[local]"

Vexor provider configuration covers remote and local setup. From the environment that starts the MCP client, verify the selected provider with:

bash
uvx vexor doctor
Connect a client

For the standalone setup, configure the MCP client to start:

text
perenna mcp

Follow the Client setup guide for the exact client command or configuration file.

Codex and Claude Code can also install the optional memory behavior Skill:

bash
perenna skill install --agent codex# orperenna skill install --agent claude-code

Repeat --agent in one command when both clients should receive the skill. The configuration reference documents user and project scope, destinations, and replacement safeguards.

Codex and Claude Code can instead install the combined Skill and MCP connection from Perenna's repository Marketplace. Follow the Plugin setup guide and choose one setup path per client.

Perenna creates its local data under ~/.perenna/ unless another home is configured.

Add optional Git synchronization

To import, publish, or fast-forward compatible history through a private Git repository, run:

bash
perenna sync setup <repository-url>

Successful setup saves the selected remote in the Perenna home. Use perenna sync disable to return to saved local-only mode without removing the Git remote.

The configuration reference owns remote selection, credentials, conflict handling, and recovery details.

Install from source

bash
git clone https://github.com/scarletkc/Perenna.gitcd Perennauv tool install .

Source contributors should use the locked environment in the development guide.

Documentation

Start with the documentation index, then follow the path for your task:

License

MIT

Source: README.md at commit 3c9ee18

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.4.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts