AI Knowledge Platform

Turn Any Website
Into AI Knowledge.

Index your docs once. Your AI gets real answers grounded in your actual content. No hallucinations, no stale context.

Live Syncing
ResourceStatus
/api/authentication
2s ago
Indexed
/guides/getting-started
1s ago
Indexed
/sdk/python/v2
now
Syncing
Pages Indexed
4,817

Content pages crawled, embedded, and ready for AI search across the platform.

Active Users
106
Active Projects
76
Searches Served
347
CLI + MCP
AI Native

Your content, directly in their workflow.

Yavy sits between your website and LLMs. Search from the CLI, drop in a Skills package, or connect via MCP - the agent gets the exact context it needs.

Semantic Search

We embed your content so agents can find concepts, not just keywords.

Structured Context

Data is returned in clean JSON, optimized for LLM consumption.

agent_session_01

The New Standard.

Traditional scraping is fragile and noisy. We built a semantic engine that understands documentation structure, ensuring your agents get signal, not noise.

Context Aware

Intelligently chunks content based on semantic headers, not just paragraphs.

Always Fresh

Automatic re-indexing keeps your content fresh as docs change.

search-docs
live
query:"how to authenticate API requests"
Authentication94% match

Use Bearer tokens to authenticate API requests. Include your API key in the Authorization header for every request...

/docs/authentication·128 tokens
Rate Limiting87% match

Authenticated requests are limited to 1,000 requests per minute. Unauthenticated requests are limited to 60...

/docs/rate-limiting·96 tokens
API Keys72% match

Generate API keys from your dashboard under Settings. Each key is scoped to a single project...

/docs/api-keys·84 tokens
3 of 12 chunks
48ms

How it Works

From content source to AI-ready in three steps, then choose your path.

1

Input

Add your website, GitHub repo, Notion workspace, or Confluence space

2

Parse

We crawl and extract meaningful content from every page

3

Index

Content becomes a searchable knowledge base

Choose your path

CLI & Skills

Recommended

CLI + Skills Package - Search from terminal or drop a skill package into your project

CLI searchSkills work offlineFast

Serve

Alternative

MCP Server - AI assistants query your content in real-time

Real-timeAlways freshInstant
CLI & Skills

Search & Generate.

Install the Yavy CLI to search your docs from the terminal or generate portable Skills packages. Drop skills into your project and your AI loads them as local knowledge - no server connection needed.

1
Install the CLI: npm install -g @yavydev/cli
2
Run setup: yavy init
3
Search: yavy search "your query"

Claude Code users

Run /yavy:init to install the CLI, authenticate, and generate skills automatically.

See all methods
terminal
$ npm install -g @yavydev/cli
$ yavy init
◆ Which AI tools do you want to set up?
│ ◼ Claude Code (detected)
│ ◼ Cursor (detected)
│ ◻ VS Code
│ ◻ Windsurf
│ ◻ OpenCode
│
◆ Which projects do you want to set up?
│ ◼ acme/React Docs (142 pages)
│ ◼ acme/API Reference (85 pages)
│ ◻ acme/Changelog (12 pages)
│
◇ Tools configured.
│
│ Summary
│ Claude Code: .claude/skills/yavy (2 project files)
│ Cursor: .cursor/rules/yavy (2 project files + MCP)
│
└ Set up 2 tool(s) with 2 project(s). Run yavy init again to refresh.
Features

Built for the way you work.

Fast, reliable, and easy to set up.

CLI-First

Search and generate from the terminal. Works with any AI tool.

Skills Export

Generate portable skill packages for offline AI use.

Reliable

Consistent, structured responses every time.

Easy Setup

Add your source and we handle discovery and indexing.

Secure Access

OAuth 2.1 authentication with enterprise-grade security.

Flexible Access

Public sources for everyone, private for your team.

Simple, transparent pricing.

All plans include a 30-day money-back guarantee.

Product Roadmap

Where we've been and what's coming next.

Q3 2025
completed

Project Inception

Initial concept, architecture design, and core MCP protocol implementation.

  • Core MCP Server
  • Vector Database Integration
  • Semantic Search with AI Embeddings
Q4 2025
completed

Public Beta

Opening the platform for early adopters with AI tool integrations and flexible indexing.

  • AI Tools Support (Claude, Cursor, Windsurf)
  • User Dashboard & Project Management
  • Flexible URL Discovery & Crawling
Q1 2026
completed

Ecosystem Expansion

Expanding capabilities with platform integrations, portable skills, and broad AI tool coverage.

  • Platform Integrations (GitHub, Notion, Confluence)
  • Yavy CLI & Portable Skills Packages
  • Authenticated Content (Private Projects)
  • Expanded AI Tool Coverage (10+ Tools)
Q2 2026
in progress

Community & Beyond

Growing the ecosystem with communication integrations and community-driven development.

  • Communication Integrations (Slack, Discord, MS Teams)
  • Community-Driven Feature Prioritization
  • Help Shape the Roadmap
Newsletter

Stay updated with Yavy

Get updates, articles, and resources in your inbox. No spam, unsubscribe anytime.

Common Questions

We use semantic search with vector embeddings. Your AI assistant finds relevant content based on meaning, not just keywords, even when the exact terms differ from the query.