Search memory
Give Claude Code a persistent memory. Save and search past conversations with semantic search. 100% local, no API keys required.
npx -y skills add couzip/cc-forever --skill search-memoryAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Search past conversations using semantic search. Use when user asks about previous discussions or wants to recall past information.
SKILL.md
1.2 KB, as published. Nobody here has run it
Search Past Conversations
Search past conversations using semantic search.
Argument Check
If $ARGUMENTS is empty, respond: "Please provide a search query."
Search query: $ARGUMENTS
Steps
1. Execute Search
Call mcp__cc-forever-mcp__retrieve_memory:
{
"query": "$ARGUMENTS",
"n_results": 5,
"threshold": 0.3
}
2. Format Results
Display results sorted by similarity:
Related past conversations:
### 1. (Similarity: 85%)
**Question:** {past question}
**Answer:** {summary of past answer}
**Date:** {timestamp}
**Project:** {project}
---
### 2. (Similarity: 72%)
...
3. Synthesized Answer
Based on the search results, provide an answer to the user's question:
---
Based on past conversations:
{answer to the question}
No Results
If no relevant results found:
No past conversations found for "{query}".
Tips:
- Try different keywords
- Use /cc-forever:index to save conversations first