Always the freshest context
The hook reads the vault at session start, so Claude Code never opens against a brief that has gone stale since it was last written.
Auto-Inject
Claude Code SessionStart hook
Claude Code pulls a live, project-aware brief from your vault at every session start.
Overview
What Claude Code SessionStart hook does
Beyond static instruction-file blocks, Auto-Inject can install a Claude Code SessionStart hook. Rather than writing a fixed brief once, the hook queries the vault live each time a session begins and hands Claude Code the freshest project-aware context available. Because it runs at startup, there is no stale block to refresh — every new session reflects what the vault knows at that moment.
The hook derives the project from the current working directory, so opening Claude Code in one repo loads that repo's memory and switching folders switches the context automatically. In the Auto-Inject tab, this target is marked as managed by a hook rather than a static file, making it clear which agents read live memory and which read a written block.
Claude CodeHook
Why it matters
The payoff for your AI memory
Project-aware automatically
Context is derived from the working directory, so each repo's session begins with that repo's memory and no manual switching.
No file to maintain
Because the brief is generated live, there is no static block to refresh — the hook keeps Claude Code current on its own.
How it works
From first launch to reusable memory
- 1
In the Auto-Inject tab, enable the Claude Code target as a SessionStart hook.
- 2
Open Claude Code inside a project directory.
- 3
Let the hook read the vault at startup and inject project-aware context before your first message.
FAQ
Common questions
What does the 1AIVault Claude Code hook do?
It runs at Claude Code's SessionStart, reads your vault live, and injects a project-aware memory brief so each session begins with current context derived from your working directory.
Is the Claude Code hook different from a static injected block?
Yes. A static block is written once into an instruction file and refreshed manually, while the hook regenerates context from the vault at every session start, so it is always fresh and never needs refreshing.
Related
More Auto-Inject features
Auto-Inject Memory
Start new agent sessions with a fresh vault brief so important memory reaches the CLI before you repeat context.
Learn moreMinimal, Standard, Rich, and Max profiles
Choose how much memory is written into agent startup files based on the work and model context budget.
Learn moreProject-scoped injection
Auto-Inject can scope memory to the current project so agents start with context that matches the workspace.
Learn moreLocal memory, shared everywhere
Give every AI tool the same memory.
Start free, import real conversations, and reuse your memory across every AI agent you already use.