Rewindex
Auto-snapshot tool for AI agents. Reduces the risk of AI agents breaking your code by automatically saving a snapshot of every file change locally. Rewind sessions, audit code changes, and inspect diffs directly from your AI chat or the built-in dashboard. Free and safe no cloud run local.
README
Rewindex
Rewindex — Auto-snapshot tool for AI agents
Auto-snapshot tool for AI agents. Automatically backs up every file change so you can recover from AI mistakes instantly. Code worry-free. Free and local.
- 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
Works with any AI agent via MCP. Works with Git. Rewind the code that you didn't commit.
Want to understand how Rewindex works in depth? Read Learn Rewindex.
How it works
-
Every save is recorded
Every time you or your AI saves a file, Rewindex captures a snapshot automatically.
-
Sessions group your work
When your AI finishes a task, all the changes are grouped into one session. Easy to find, easy to rewind.
-
AI notes what it did
When your AI finishes a task, it writes a note on the session. You can add your own notes too.
-
Rewind without guessing
When something breaks, the full log is right there. Your AI knows exactly where to go back to.
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 instructions per agent (Claude Code, Cursor, Windsurf, OpenCode, Hermes, and others)
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
- Learn Rewindex: everything you need to know about Rewindex as a user
- AI Agent Setup: install guide for AI agents with per-agent MCP setup
License
Proprietary. See LICENSE for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.