Summary
This adds vector search to Claude using AgentDB, which claims 150x to 12,500x faster operations than traditional vector databases with sub-100 microsecond search times. It uses HNSW indexing and quantization under the hood. You'll need Node.js 18+, AgentDB v1.0.7+, and an OpenAI API key for embeddings, though custom models work too. The setup is straightforward with a CLI init command. Worth considering if you're building semantic search features and speed matters, though the performance claims are aggressive enough that you'd want to benchmark against your own data. It's part of the larger ruflo skill collection from ruvnet.
Install to Claude Code
npx -y skills add ruvnet/ruflo --skill "AgentDB Vector Search" --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
