Marketplace for Claude Memory - semantic search for Claude Code conversation history
npx claudepluginhub kamrul1157024/claude-memoryIndex and search Claude Code conversation history with semantic search. Find previous discussions, recall solutions, and retrieve context from past coding sessions.
Index and search Claude Code conversation history with semantic search.
# Clone and install
git clone https://github.com/kamrul1157024/claude-memory.git
cd claude-memory
pip install -e .
# Download embedding model
claude-memory models download
# Initialize and index
claude-memory init
claude-memory index
# Search conversations
claude-memory search "what async patterns do I use"
# Index new conversations
claude-memory index
# View stats
claude-memory stats
# Show specific conversation
claude-memory show <conversation-id>
Install claude-memory as a Claude Code plugin to search your conversation history.
# Add the marketplace
/plugin marketplace add kamrul1157024/claude-memory
# Install the plugin
/plugin install claude-memory
Copy the skill directory to your Claude skills folder:
cp -r skills/claude-memory ~/.claude/skills/
Or create a symlink:
ln -s $(pwd)/skills/claude-memory ~/.claude/skills/claude-memory
In Claude Code, you can now ask:
Claude will automatically invoke the skill and search your indexed conversation history.
Claude will naturally discover facts about you during conversations (technologies you use, preferences, patterns). When it discovers useful facts, it will ask for your confirmation before saving them to ~/.claude/CLAUDE.md.
# macOS native build
make build-macos
make install
# Linux via Docker
make build-docker
Config is stored at ~/.claude-memory/config.yaml:
active_models:
embedding: nomic-embed-text-v1.5
Change the embedding model:
claude-memory config set active_models.embedding bge-small-en-v1.5
claude-memory models download bge-small-en-v1.5
claude-memory index --full # Re-index with new model
MIT
Official prompts.chat marketplace - AI prompts, skills, and tools for Claude Code
Open Design — local-first design app exposed to coding agents over MCP. Install once with your agent's plugin command and projects/files/skills are reachable through stdio.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations