Right-sized for the model
Match the brief to the context window in front of you — a lean 600 tokens for small models, up to 8,000 when you have room to spare.
Auto-Inject
Minimal, Standard, Rich, and Max profiles
Dial the injected brief from a 600-token snippet up to an 8,000-token deep context.
Overview
What Minimal, Standard, Rich, and Max profiles does
Auto-Inject ships four size profiles so the brief fits both the task and the model's context budget. Minimal keeps roughly 600 tokens of only the most critical saved context; Standard is the balanced 1,800-token default; Rich expands to around 3,500 tokens; and Max carries up to 8,000 tokens for the deepest project recall. Rich and Max are Pro profiles.
Bigger is not always better. A large brief eats into the window the agent needs for actual work, while too small a brief leaves out context you rely on. Picking a profile lets you trade depth of detail against tokens spent — tighten the injection for quick edits, and widen it when you want the agent to hold the whole project in mind.
ProfilesContext
Why it matters
The payoff for your AI memory
Protect the working window
Smaller profiles leave more room for code and reasoning, so injected memory never crowds out the task the agent is actually there to do.
Scale up on Pro
Rich and Max unlock deeper 3,500- and 8,000-token briefs when a project needs the agent to start with more history than the free profiles carry.
How it works
From first launch to reusable memory
- 1
Open the Auto-Inject tab and find the profile selector.
- 2
Choose Minimal, Standard, Rich, or Max based on the work and your context budget.
- 3
Preview the resulting brief to confirm its size, then refresh to write it.
FAQ
Common questions
What is the difference between the Minimal, Standard, Rich, and Max profiles?
They set how much memory is injected: Minimal is about 600 tokens of critical context, Standard about 1,800, Rich about 3,500, and Max up to 8,000 tokens. Rich and Max are Pro profiles.
Which injection profile should I use?
Standard suits most work as a balanced default. Drop to Minimal for small context windows or quick tasks, and move to Rich or Max when you want the agent to start with deeper project history.
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 moreProject-scoped injection
Auto-Inject can scope memory to the current project so agents start with context that matches the workspace.
Learn morePreview and refresh
Preview exactly what will be written, refresh context on demand, and see stale classification or import gaps first.
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.