CP Memory

io.github.CJhuochaiPublished by GitHub account CJhuochaiv1.8.1Updated Oct 24, 2026

Local-first, governable long-term memory for AI coding agents

The publisher's own server: Memory.fit

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

CP Memory gives an AI coding agent a local, reviewable long-term memory store so project rules and decisions persist across sessions.

What you can do
It stores facts, preferences, ongoing work, episodes, decisions, and conversation checkpoints in a local SQLite database and restores relevant context through MCP tools and lifecycle hooks. It can automatically extract conservative memory candidates from explicit statements, prioritize current-project memories by repo, project, and workspace scope, and support review inboxes, digests, conflict suggestions, and correction states. Memories can be marked wrong, stale, or scoped instead of being silently overwritten.
When to use it
Use it when you want a coding assistant to remember project rules, preferences, and decisions across sessions without relying on a hosted memory service. It suits users who want to inspect, correct, and govern what is remembered rather than accumulate everything.
Requirements
Runs as a local stdio process. The portable path needs Python 3.10+ and uv, started with uvx cp-memory-mcp. The enhanced Codex plugin path uses a marketplace install on Windows or a source installer on macOS/Linux that creates a private Python runtime. No authentication, environment variables, or headers are declared.
Before you install
Memory is written to a local SQLite database, by default under the user's home directory, and automatic extraction creates memory candidates from explicit statements. Do not commit the memory database, logs, private summaries, or environment files. Review reminders are injected into assistant context rather than shown as a user-facing panel, and maintenance does not auto-delete memory or auto-resolve conflicts.

Installation

In SourceWeft

  1. Open CP Memory 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

[CP Memory logo]

CP Memory

Local-first, governable memory for AI coding agents.
Remember project rules across sessions, recall only what matters, and correct bad memory without hiding history.

简体中文 | English

[License: MIT] [Local first] [MCP server] [Cross-platform CI]


Why CP Memory

For reproducible package, protocol and recall checks, see verification evidence and limits.

  • Local first: memory stays in ~/.cp-memory/memory.db by default.
  • Governable: inspect, review, correct, scope, or retire memory instead of silently overwriting it.
  • MCP-ready, Codex-enhanced: the stdio MCP server is the portable baseline; the Codex plugin adds Skills and lifecycle Hooks.

[CP Memory 30-second demo]

Quick Start — Portable MCP

With Python 3.10+ and uv installed, any stdio MCP client can start CP Memory with:

text
uvx cp-memory-mcp

The public package passed a clean-cache MCP handshake with all 40 tools and a write/search/correct flow. See MCP client setup for Codex, Claude Code, Cursor, VS Code, and Gemini CLI examples.

For the enhanced Codex integration with lifecycle Hooks and Skills, install the plugin:

powershell
codex plugin marketplace add CJhuochai/cp-memorycodex plugin add cp-memory@cp-memory

Restart Codex after installation and approve the lifecycle Hooks if prompted.

See The Result In 30 Seconds

  1. Tell Codex a project rule, such as: “Releases must start on a branch, run tests, and merge through a PR.”
  2. In a later session, CP Memory restores the relevant rule from the local primary store so Codex can continue following it.
  3. If the rule is wrong, preserve correction history and mark the old record wrong, stale, or scoped instead of silently overwriting it.

CP Memory is a local-first memory plugin for Codex. It stores facts, preferences, ongoing work, episodes, decisions, and conversation checkpoints in a local SQLite database, then restores relevant context through MCP tools and lifecycle hooks.

The goal is not to remember as much as possible. The goal is memory that remains trustworthy after long-term use: explainable, reviewable, correctable, and governable.

[CP Memory architecture]

[CP Memory recall demo]

Current Capabilities

  • Context restore: restores relevant local-primary memory on startup and eligible prompts.
  • Automatic extraction: conservatively creates long-term personal memory candidates from explicit statements.
  • Project scope: prioritizes current-project memories with repo:, project:, and workspace: scopes.
  • Reviewable governance: supports review inbox, review digests, conflict suggestions, correction states, and startup reminders.
  • Safe maintenance: weekly maintenance runs health checks, governance preflight, and low-risk expiry cleanup only.

[CP Memory governance loop]

30-Second Example

You tell Codex:

text
Remember this: releases for this project must start on a branch, run tests, and merge through a PR.

In a later session, you ask:

text
What are the release rules for this plugin?

CP Memory restores the relevant memory from the local primary store first, and Codex follows that rule. If the memory is wrong, you can mark it wrong, mark it stale, or write a corrected version.

See more anonymized examples in docs/examples.md.

For a GIF, short video, or launch post, use the sanitized 30-second demo script.

Install

For any stdio MCP client, use the verified public package:

text
uvx cp-memory-mcp

Client-specific commands and JSON files are in docs/mcp-clients.md.

For Windows, the recommended path is GitHub Marketplace installation:

powershell
codex plugin marketplace add CJhuochai/cp-memorycodex plugin add cp-memory@cp-memory

Restart Codex after installation. If Codex asks you to trust hooks, approve the CP Memory lifecycle hooks in the hooks view.

For macOS/Linux, use the source installer. It creates a private Python runtime for the plugin and installs the MCP dependency:

sh
git clone https://github.com/CJhuochai/cp-memory.gitcd cp-memorysh ./install.sh

Restart Codex when it finishes. Do not treat GitHub Marketplace installation on macOS/Linux as an equivalently verified path: Marketplace does not run install.sh, so it does not create that private runtime.

Platform Support

PlatformRecommended installationVerified coverage
WindowsGitHub Marketplace; install.ps1 for local developmentUnit tests, isolated installation validation, and GitHub Actions CI passed
macOSSource installer: sh ./install.shGitHub Actions macOS CI passed unit tests and isolated install/MCP startup validation
LinuxSource installer: sh ./install.shGitHub Actions Ubuntu CI passed unit tests and isolated install/MCP startup validation

Manual smoke testing of real Codex desktop Hook injection on macOS/Linux is still pending access to physical devices. This release is accepted through three-platform CI; the boundary does not affect the installer and MCP-startup checks already covered, but it is not a substitute for full desktop manual acceptance.

Safety

  • Do not commit your real memory.db, logs, private summaries, or environment files.
  • Automatic extraction is intentionally conservative. Generated memories can be reviewed, corrected, marked stale, or marked wrong.
  • When memories need review, the current version injects a reminder into assistant context. It is not a user-facing popup or visible review panel, and it does not auto-delete memory or auto-resolve conflicts.
  • Weekly maintenance runs health checks, governance preflight, and low-risk expiry cleanup only; long-term personal memories, tasks, and decisions are protected by default.
  • Examples and screenshots use sanitized content, so you do not need to expose your real memory database.

Comparison

If you have seen other memory projects, start with docs/comparison.md. CP Memory's main difference is Codex lifecycle integration plus memory governance, not just storage and search.

Roadmap

See docs/roadmap.md for future directions. The roadmap prioritizes local-first behavior, explainability, correctability, and privacy safety.

See CHANGELOG.md for version history.

Local Development

Windows users normally do not need to run install.ps1. It is mainly for local development, refreshing the personal marketplace cache, and migrating old global hook wiring from earlier versions.

For local macOS/Linux development, run:

sh
sh ./install.shsh ./scripts/test-install.sh

Python 3 with python3 on PATH is required. The installer creates a private virtual environment in the plugin directory and installs runtime dependencies; this is the currently verified installation path for macOS/Linux.

Run the test suite:

powershell
python -m unittest discover -s tests -p test_cp_memory.py

Validate the installer in an isolated temporary profile without touching your real Codex configuration:

powershell
powershell -ExecutionPolicy Bypass -File .\scripts\test-install.ps1

License

MIT

Source: README.md at commit a584f64

Tools

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

Version history

1
  1. v1.8.1LatestSep 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

Other Memory integrations