Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions .github/workflows/daily-hippo-learn.md
Original file line number Diff line number Diff line change
Expand Up @@ -90,6 +90,17 @@ This runs the complete cycle: learn from commits, import any `MEMORY.md` files,
consolidate by applying decay, merge near-duplicates, and promote high-value lessons
to the global store.

## Step 2.5 — Refresh embeddings

Keep the vector index current so semantic recall stays sharp. Run after every sleep
cycle to embed any memories that were added or updated since the last embed pass:

```
mcpscripts-hippo args: "embed"
```
Comment on lines +93 to +100
Copy link

Copilot AI Apr 24, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The new mcpscripts-hippo args: "embed" step will fail in this workflow because @xenova/transformers (required by hippo embed, per the PR description) is never installed here. Add a setup steps: entry (similar to hippo-embed.md) to install the dependency, and re-run the workflow compiler so the change is reflected in daily-hippo-learn.lock.yml (the lock file is what GitHub Actions executes).

Copilot uses AI. Check for mistakes.

This is fast for incremental updates (only unembedded memories are processed).

## Step 3 — Recall top insights

Recall memories across these four lenses (run each separately):
Expand Down
Loading
Loading