Sonnet 4.5

Pick a model and we can get started!

Memory
Manage what surfaces in context.
People & topics
People and topics your AI keeps ongoing summaries about.
Concepts
Named narrative patterns that shape context automatically.
Files & Artifacts
Uploaded files, attachments, and saved creative or technical work.
Profile settings
Identity
Your name
Instance name
Model
AI model for this profile
Use Haiku (testing mode)
Use a faster, cheaper model for testing
Temperature
How varied or predictable responses feel. Locked at 1.0 when extended thinking is on.
1.0
Extended thinking
Lets the AI think step-by-step before responding.
Thinking depth
How long the AI can think before responding
Conversation window
How much recent conversation the AI sees at once
All profiles
Retrieval sensitivity
How closely memories must match to get shown to AI. Lower is broader.
0.25
Memory retrieval limit
How many past messages get surfaced per response
10
Topic profiles per turn
How many people and topic profiles get loaded each turn
3
Concepts per turn
How many keyword-triggered background entries load per response
2
Recent files shown
How many recent file attachments the AI is aware of
5
Retrieval weights
Controls how memories are ranked when retrieved. Meaning how closely they match what you're saying Importance how significant they were Recency how recent Topics whether they involve the same people or subjects
Meaning 0.4
Importance 0.25
Recency 0.15
Topics 0.20
Deep archive age
Messages older than this require @recall --deep to search
180
Profile settings
Features
Narrative concepts
Background knowledge that activates based on keywords
Topic profiles
Remembered profiles of people and topics
File attachments
Images, PDFs, text, and JSON files
Text-to-speech
Read responses aloud. Requires an ElevenLabs API key.
Timeline
Daily summaries of your recent conversations, last 7 days
AI Notes
Notes the AI keeps about you and ongoing topics
System instructions
Placeholders like {instance_name} and {max_iterations} are filled in automatically — keep them as-is.
All profiles
API Keys
Keys are stored locally and sent only to their respective providers
Anthropic
OpenAI
ElevenLabs
All profiles
Embeddings
How your messages are indexed for memory search. Re-index if you switched to on-device embeddings or imported older messages.
All profiles
Keep this PC awake while Mneme is running
Stops the computer from sleeping so phones and other devices can stay connected. The screen can still turn off.
Transcript
Download this profile's conversation
Context budgets
Recent — Memory — Entity — Concept —
Memory tiers
Active — Standard — Deep archive —
View usage on Anthropic Console
AI is thinking

Make the window a little taller to use Mneme

Mneme is designed for your phone
This runs on your computer, but the best experience is from your phone's browser via Tailscale.

If the installer set up Tailscale, just install the Tailscale app on your phone, sign in with the same account, and visit this address:
You can always use it from desktop too — this is just a heads up!
Migrate to new embeddings
Move your memories to a safer home