Convert gitgram/ and aitimemachine/ from embedded git repos (which showed as opaque submodule gitlinks on GitHub) into fully-tracked first-party content. AITM now merges its 7 vendored repos as first-party engines: - memory: beads (Go task DAG) + context7 (docs SDK), unified into saved_contexts - git: vendored C git (bundled binary) + gitnexus (in-process code intelligence) - agentic: a2a (@a2a-js/sdk) + pal (AITM-managed Python subprocess) Includes the full session's product build: Gitgram web/mobile/backend features, AITM website/CLI/MCP, the unified memory layer, engine build tooling (scripts/build-engines.sh, Dockerfile, CI), docs (README, ENGINES.md, ARCHITECTURE.md), and extensive test suites. Build artifacts, node_modules, external/, and gemini-cli are gitignored. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
1.4 KiB
1.4 KiB
sidebar_position
| sidebar_position |
|---|
| 1 |
Welcome to AITimeMachine
AITimeMachine is an open-source infrastructure tool that provides a "Time Machine" for AI coding assistants. It allows users to create timestamped snapshots of code and conversations, enabling easy reversion to past states and preventing data loss from AI memory resets.
Key Features
- Timestamped Snapshots: Capture exact code states with timestamps.
- Conversation Memory: Persistent logging of AI interactions across sessions.
- User Confirmation Gates: Optional prompts before AI modifications.
- Time Travel: Browse and revert to any historical snapshot.
- MCP Protocol Support: Seamless integration with AI tools via Model Context Protocol.
- Cross-Platform: Works on Windows, Mac, and Linux.
Quick Start
Installation
npm install -g aitimemachine
Basic Usage
-
Initialize in your project:
aitm init . -
Log conversations:
aitm log user "Build a React component" aitm log assistant "Here's the code..." -
Create snapshots:
aitm snapshot -
View history:
aitm list -
Revert if needed:
aitm revert 0
For AI Tool Integrators
Run the MCP server for AI assistants:
aitm mcp
This exposes tools for automatic snapshotting and conversation logging.