Linkly AI
Local document search engine that exposes your files to AI agents over MCP
Linkly AI indexes documents on your own machine and makes them retrievable by AI agents through MCP or Agent Skills.
It reads PDF, DOCX, PPTX, EPUB, Markdown, HTML, images via OCR, and audio and video via transcription. Indexing, search, OCR and semantic search all run locally, so files stay on the device unless a cloud library is deliberately created. It runs on macOS, Windows and Linux, and works fully offline with an official model pack.
Any MCP-speaking client can connect, including Claude, Claude Code, ChatGPT, Cursor, Codex and OpenClaw. The desktop app and all local features are free with no cap on indexed files; paid plans add frontier models, remote access and larger cloud quotas.
Pricing: Monthly subscriptions
Choosing an AI search API right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing an AI search API right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Linkly AI Alternatives
Explore 49 products in the Frameworks & Stacks category. View all Linkly AI alternatives.
GPT4All
Desktop app and Python SDK for running open-source LLMs locally on any device
LocalAI
Open-source, self-hosted OpenAI-compatible API for running models on your own hardware
Magnitude
Open-source desktop inference engine that tunes its kernels to your hardware and connects local models to your agent.
AGNT
Local-first desktop workspace for building and running agents, with visual workflows, memory and MCP connections
CloudPloy
MCP server that lets a coding agent deploy apps to your own servers or cloud account
Work on Linkly AI? Feature it at the top of Frameworks & Stacks.
Is your product missing?