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>
1.3 KiB
1.3 KiB
sidebar_position
| sidebar_position |
|---|
| 3 |
Usage
CLI Commands
Initialize
aitm init [projectPath]
Initializes AITimeMachine for a project. Creates the .aitimemachine directory.
Log Conversation
aitm log <role> <message>
Logs a conversation entry. Role can be user or assistant.
Example:
aitm log user "Create a login form"
aitm log assistant "Here's the React component..."
Create Snapshot
aitm snapshot [filePath]
Creates a timestamped snapshot of the current code state and conversation.
List Snapshots
aitm list
Displays all snapshots with timestamps and conversation counts.
Revert to Snapshot
aitm revert <index>
Reverts code and conversation to the specified snapshot index.
MCP Server
aitm mcp
Runs the MCP server for AI tool integrations.
MCP Integration
For AI tools supporting MCP:
- Start the MCP server:
aitm mcp - Configure your AI tool to connect to the MCP endpoint.
- Use tools like
create_snapshotbefore edits andlog_conversationfor memory.
Available MCP Tools:
create_snapshot:{ filePath?: string }list_snapshots:{}revert_to_snapshot:{ index: number }log_conversation:{ role: "user" | "assistant", message: string }get_conversation:{}