Adopt cf_core.memory (mnemo) for persistent knowledge graph #25

Open
opened 2026-06-03 18:33:58 -07:00 by pyr0ball · 0 comments
Owner

Summary

Once circuitforge-core#63 lands (mnemo as a shared cf_core.memory module), raven should adopt it.

raven-specific use

BCI/adaptive input: gesture calibration history, command mapping preferences, which input modes work best under which conditions. Persistent model of the user's adaptive input patterns and ergonomic needs over time.

Implementation

No product-level implementation needed beyond:

  1. Adding the mnemo sidecar to the product compose stack (via cf-core compose template)
  2. Calling cf_core.memory.remember(conversation) after each user interaction
  3. Calling cf_core.memory.recall(query) to inject relevant context into prompts

Linked

## Summary Once circuitforge-core#63 lands (mnemo as a shared `cf_core.memory` module), raven should adopt it. ## raven-specific use BCI/adaptive input: gesture calibration history, command mapping preferences, which input modes work best under which conditions. Persistent model of the user's adaptive input patterns and ergonomic needs over time. ## Implementation No product-level implementation needed beyond: 1. Adding the `mnemo` sidecar to the product compose stack (via cf-core compose template) 2. Calling `cf_core.memory.remember(conversation)` after each user interaction 3. Calling `cf_core.memory.recall(query)` to inject relevant context into prompts ## Linked - circuitforge-core#63: mnemo module implementation - https://github.com/zaydmulani09/mnemo — upstream project (MIT license)
Sign in to join this conversation.
No labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference: Circuit-Forge/raven#25
No description provided.