mcpField
R
Rewindex - Auto-snapshot tool for AI agents. Auto backup, Avoid the mistakes of AI.

Rewindex - Auto-snapshot tool for AI agents. Auto backup, Avoid the mistakes of AI.

Local
github.com/crsxmdVersion Control1Updated 22w ago

About Rewindex - Auto-snapshot tool for AI agents. Auto backup, Avoid the mistakes of AI.

Rewindex is a local snapshot and recovery tool for AI-driven code changes. It helps developers audit file history, inspect diffs, and restore uncommitted work through a built-in dashboard or AI chat.

Key features

  1. 01Automatically captures file changes
  2. 02Snapshots, rewind, and change history
  3. 03Diffs and session logs
  4. 04Milestone flags and changelog export
  5. 05Audit and restore code in dashboard

Use cases

  1. 01Review files changed by an AI agent
  2. 02Trace when a code issue began
  3. 03Restore uncommitted code changes

MCP support

Rewindex works as an MCP server with AI agents, allowing snapshots to be reviewed and restored from an AI chat.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Rewindex MCP

python license PyPI Downloads

rewindex

Rewindex - Reduce the risk of AI breaking your code.

Records what your AI changed before you realize something broke. Audit and recover from your AI chat or the built-in dashboard. Free, runs locally.

  • Versioning: snap, rewind, and track every change your AI makes
  • Change visibility: view diffs, session logs, and full file history
  • Changelog: flag milestones and export as CHANGELOG.md
  • Audit code: let your AI review and audit it, or browse it yourself via the built-in dashboard

Works with any AI agent via MCP. Works with Git. Rewind the code that you didn't commit.

rewindex.org | GitHub

Want to understand how Rewindex works in depth? Read Learn Rewindex.


What you get

  • Auto backup - every file change is captured automatically. Nothing is ever lost.
  • Built-in dashboard - browse snapshots, view diffs, and rewind from the browser or your AI chat. No extra install. No coding required.
  • Free to start - free forever. No credit card. Upgrade only when you need more.
  • Runs locally - everything stays on your machine. No cloud. No account required.
  • Audit code - your AI already knows which file to check. Give it a bug and it traces that file's history to find exactly when it broke.
Try it! Then ask your AI if it likes it.

Quick Start

Supported platforms: macOS, Linux, and Windows (beta).

Requires Python 3.10+.


AI agent setup (recommended)

Paste this into your AI agent's chat. It handles everything including install, MCP setup, and init:

Read https://raw.githubusercontent.com/crsxmd/rewindex/main/AI-SETUP.md and follow the setup instructions.

Manual setup

1. Install

pipx install rewindex   # recommended
pip install rewindex    # alternative
uv tool install rewindex

2. Add as MCP server — see mcp-register.md for per-agent instructions

Supported agents: Claude Code, Cursor, Windsurf, Cline, Roo Code, Continue, GitHub Copilot, Gemini CLI, Codex CLI, OpenCode, Warp, OpenHands, Goose, Augment, Kilo Code, Junie, Hermes, and more

3. Initialize your workspace

rewindex init           # interactive — asks for workspace name and folder

Dashboard

rewindex web

Open http://localhost:9009 — browse snapshots, view diffs, rewind files, manage flags and settings. Included in the package, no extra install needed.


Pricing

Free forever. No account required.

Want to upgrade? Check rewindex.org


Documentation


License

Proprietary. See LICENSE for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.