<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Linkly AI</title><description>Local Search Engine, Built for AI Agents.</description><link>https://linkly.ai/</link><item><title>v0.4.0 Release: Chat with Tens of Thousands of Your Local Files</title><link>https://linkly.ai/blog/v040-chat-with-local-files/</link><guid isPermaLink="true">https://linkly.ai/blog/v040-chat-with-local-files/</guid><description>Linkly AI v0.4.0 introduces Linkly AI Chat — talk to thousands of your notes, PDFs, journals, and project records without ever leaving Linkly. Plus a new Data Privacy panel, local model download progress, in-app changelog, MDX support, and three new languages: Japanese, French, and Spanish.</description><pubDate>Thu, 30 Apr 2026 00:00:00 GMT</pubDate></item><item><title>What Can AI Do with 10,000 Local Documents? 12 Real Scenarios</title><link>https://linkly.ai/blog/12-real-tasks-on-10000-local-docs/</link><guid isPermaLink="true">https://linkly.ai/blog/12-real-tasks-on-10000-local-docs/</guid><description>From building a resume to digging up visa paperwork, from startup retrospectives to searching a 240,000-word ebook — 12 things I actually did with AI on my own 10,000 local documents.</description><pubDate>Mon, 30 Mar 2026 00:00:00 GMT</pubDate></item><item><title>v0.3.0 Release: Library Management, Finally Complete</title><link>https://linkly.ai/blog/v030-library-management/</link><guid isPermaLink="true">https://linkly.ai/blog/v030-library-management/</guid><description>Linkly AI v0.3.0 introduces library management — organize folders by project or topic, and switch search scope with a single keystroke. MCP tools and CLI are also upgraded so AI Agents can leverage your library structure.</description><pubDate>Mon, 30 Mar 2026 00:00:00 GMT</pubDate></item><item><title>v0.2.2 Release: Text in Images Is Now Searchable</title><link>https://linkly.ai/blog/v022-ocr-image-search/</link><guid isPermaLink="true">https://linkly.ai/blog/v022-ocr-image-search/</guid><description>Linkly AI v0.2.2 adds local OCR to automatically extract text from PNG, JPG, BMP, and WEBP images and index it. Screenshots, scans, whiteboard photos — if it has text, you can find it.</description><pubDate>Thu, 19 Mar 2026 00:00:00 GMT</pubDate></item><item><title>v0.2.0 Release: Connect Your Local Knowledge Base to Online AI</title><link>https://linkly.ai/blog/v020-remote-tunnel-release/</link><guid isPermaLink="true">https://linkly.ai/blog/v020-remote-tunnel-release/</guid><description>Linkly AI v0.2.0 introduces Remote Tunnel, letting ChatGPT, Claude.ai, and other cloud-based AI apps access your local knowledge base through a secure tunnel. Your documents stay on your machine — nothing goes to the cloud.</description><pubDate>Sat, 14 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Three Generations of PKM: From Folders to AI Collaboration</title><link>https://linkly.ai/blog/pkm-evolution-ai-second-brain/</link><guid isPermaLink="true">https://linkly.ai/blog/pkm-evolution-ai-second-brain/</guid><description>Evernote, Obsidian, Notion AI — personal knowledge management tools have undergone three paradigm shifts. But the real breakthrough of the 3.0 era isn&apos;t about which tool is smarter. It&apos;s about letting AI work across all tool boundaries, on your complete knowledge base.</description><pubDate>Fri, 13 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Why the Command Line May Be the Most AI-Agent-Friendly Interface</title><link>https://linkly.ai/blog/cli-best-interface-for-ai-agents/</link><guid isPermaLink="true">https://linkly.ai/blog/cli-best-interface-for-ai-agents/</guid><description>Claude Code, Codex CLI, Gemini CLI — top AI companies have independently converged on the command line. This isn&apos;t nostalgia; it&apos;s because CLI is naturally suited to AI Agents across three dimensions: composability, predictability, and auditability.</description><pubDate>Thu, 12 Mar 2026 00:00:00 GMT</pubDate></item><item><title>The Researcher&apos;s AI Workflow: How to Let AI Read 1,000 Papers</title><link>https://linkly.ai/blog/researcher-ai-workflow-managing-1000-papers/</link><guid isPermaLink="true">https://linkly.ai/blog/researcher-ai-workflow-managing-1000-papers/</guid><description>You have 1,000 papers in Zotero, but you still Google Scholar every time you write a review? This post walks through a practical workflow: let Claude search, browse, and read your local literature library.</description><pubDate>Wed, 11 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Why We Believe Local-First Is Becoming More Important in the AI Era</title><link>https://linkly.ai/blog/privacy-first-local-ai-knowledge-base/</link><guid isPermaLink="true">https://linkly.ai/blog/privacy-first-local-ai-knowledge-base/</guid><description>AI multiplies both the value and the risk of your data. Meanwhile, local compute power, the AI agent toolchain, and your own digital assets are all pointing toward the same conclusion: local-first is not a fallback—it&apos;s the future.</description><pubDate>Tue, 10 Mar 2026 00:00:00 GMT</pubDate></item><item><title>When AI Can Access Your Local Files: How Conversations with Claude Change</title><link>https://linkly.ai/blog/before-after-local-docs-transform-claude/</link><guid isPermaLink="true">https://linkly.ai/blog/before-after-local-docs-transform-claude/</guid><description>Claude is smart, but it has no idea what&apos;s in your files. Connect your local documents, and what it can do for you changes completely — here are 4 real-world scenarios.</description><pubDate>Mon, 09 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Why We Abandoned RAG: Six Fundamental Problems</title><link>https://linkly.ai/blog/why-we-abandoned-rag/</link><guid isPermaLink="true">https://linkly.ai/blog/why-we-abandoned-rag/</guid><description>We spent months building a complete RAG pipeline. It was technically elegant, but we had to admit: it wasn&apos;t good enough. Here are the six root problems we encountered, and how we solved them.</description><pubDate>Sun, 08 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Without Leaving the Terminal, Let AI Search Every Document on Your Computer</title><link>https://linkly.ai/blog/ai-search-docs-without-leaving-terminal/</link><guid isPermaLink="true">https://linkly.ai/blog/ai-search-docs-without-leaving-terminal/</guid><description>A lightweight Rust CLI tool that connects to the Linkly AI desktop app, enabling you to search, browse, and read local documents from your terminal. It also serves as an MCP bridge for AI agents to access Linkly AI.</description><pubDate>Sat, 07 Mar 2026 00:00:00 GMT</pubDate></item><item><title>One Command to Let Claude Code and 30+ AI Tools Read Your Local Files</title><link>https://linkly.ai/blog/one-command-ai-tools-read-local-files/</link><guid isPermaLink="true">https://linkly.ai/blog/one-command-ai-tools-read-local-files/</guid><description>A skill pack following the Agent Skills open standard. Once installed, 30+ AI platforms including Claude Code and Codex CLI can directly search, browse, and read your local documents.</description><pubDate>Sat, 07 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Outlines Index: A Progressive Disclosure Approach for Feeding Documents to AI Agents</title><link>https://linkly.ai/blog/outlines-index-progressive-disclosure-for-ai-agents/</link><guid isPermaLink="true">https://linkly.ai/blog/outlines-index-progressive-disclosure-for-ai-agents/</guid><description>Traditional RAG splits documents into chunks and feeds them to AI. We took a different approach: build a structured outline for each document, letting AI browse like a researcher — scan the table of contents, navigate to relevant sections, then read precisely.</description><pubDate>Sat, 07 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Linkly AI: Let AI Agents Access Your Local Documents Without Friction</title><link>https://linkly.ai/blog/introducing-linkly-ai/</link><guid isPermaLink="true">https://linkly.ai/blog/introducing-linkly-ai/</guid><description>Your contracts, reports, papers, and proposals are AI&apos;s &apos;dark matter.&apos; Traditional RAG chops documents into fragments and feeds them to AI — with poor results. We took a different approach: let AI browse your file cabinet like a researcher.</description><pubDate>Wed, 04 Mar 2026 00:00:00 GMT</pubDate></item></channel></rss>