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