Knowhere

Knowhere 2.0 is live. 🚀 Real-world documents don’t fit neatly into Markdown—and agents often get lost as the knowledge base grows. 2.0 adds dual-track parsing and agent-native retrieval, helping agents understand more files and decide what to read next. Read more 👇 medium.com/@13512395620/know…

3,000 GitHub stars in just 3 months. ⭐ We’re genuinely blown away.🤗 We built Knowhere because turning documents into Markdown isn’t enough. AI agents need structured memory they can navigate, retrieve, cite, and reason over. Here’s what we built beyond MinerU—and why it resonated 👇 medium.com/@13512395620/how-…

Current AI has the exact same brain damage as a famous medical patient from 1953. Think about it: you tell an LLM your entire life story, start a new chat, and poof—it doesn't even know your name. Most people think this is a compute problem. It’s not. 70 years ago, a neurosurgeon removed a patient’s hippocampus. The result? The man literally couldn't form new memories. He was trapped in 1953 forever. That single surgery proved memory isn’t one big storage drive. It’s 7 distinct biological layers working together. Knock one out, and everything breaks. Today, we're essentially trying to cure AI of that exact condition—by copying biology to patch in those missing layers. Broke down the full story and what it means for the next generation of agents👇： medium.com/@13512395620/ais-…

Lately, our team rolled out a new visual parsing route for Knowhere: VISION-MAP. We built it because traditional text chunking completely ruins complex tables, stamps, and engineering drawings. Once you flatten a layout into Markdown, the relations between data points just disappear. With this pipeline, the AI navigates the document tree to find the right candidate pages, then reads the raw page visually—keeping every answer tied to the exact source page. It's mainly for finance, engineering, and compliance tasks where guessing isn't an option and you need proof. Put together a write-up on the architecture and how to use it over on Medium. Give it a read if you're curious: medium.com/@13512395620/how-…

A lot of AI agent problems start before the LLM ever sees the data. Bad parsing → bad context → bad answers.❌️ PDF parsing isn’t just plumbing anymore. It’s part of the AI stack. I put together a practical look at Reducto, LlamaIndex, Unstructured, MinerU, and Knowhere — and when each one actually makes sense.👍 Hope this helps others make more informed technical decisions and choose the right tools for their use case. medium.com/@13512395620/how-…

We kept seeing the same question from users: “Can I connect Knowhere to my own agent?” So we built that. Knowhere Notebook and Knowhere MCP are live. Manage your docs in Notebook. Mount the same library into Cursor, Claude Code, Codex, and other MCP clients. Same account. Same cloud Brain. Search from your agent — or, with Full access, parse new docs straight back into Knowhere. If you’ve been waiting for this, go try it and tell us what breaks / what’s missing. medium.com/p/knowhere-can-no…

The biggest lesson we've learned from building RAG systems: Better models don't automatically create better products. In practice, most of the work goes into evaluation, data quality, and preserving the context behind enterprise knowledge—not model training. Reliable AI starts with reliable information. That's the philosophy behind everything we build at Knowhere. medium.com/p/does-90-of-a-ra…

🎉 1 month. 1,500+ GitHub Stars. Thank you to everyone who starred, contributed, and tried Knowhere. ❤️ Most document tools stop at parsing PDFs into Markdown. Knowhere goes one step further. We turn documents into AI-ready memory by preserving hierarchy, linking tables and images, and organizing knowledge for Agentic RAG and AI Agents. ✨ Better retrieval ✨ Richer context ✨ Structured memory instead of fragmented chunks If you're building RAG, enterprise knowledge bases, or AI Agents, give Knowhere a try and see the difference. 🔧GitHub：github.com/Ontos-AI/knowhere 🌐Knowhere：knowhereto.ai/?utm_source=x ⭐ Star the repo. Test it with your own documents. Tell us what you'd build. #OpenSource #RAG #AIAgents #LLM #GenAI Read more about Knowhere👇 medium.com/p/1-500-stars-in-…

I just finished reading and mapping out my thoughts on Microsoft Research’s latest framework, SkillOpt. As someone looking at the AI landscape from an operational perspective, this approach genuinely shifts how we think about agent optimization. When deploying AI Agents in real-world scenarios, we usually get stuck between two suboptimal paths: 1️⃣ Heavy Reliance on Manual Prompts: It’s a game of whack-mole. You fix a prompt bug in one place, only to trigger unexpected hallucinations in another as complexity scales. 2️⃣ Model Fine-Tuning (SFT): Not only is it compute-heavy, but the moment a base model upgrades, your hard-earned fine-tuned weights become obsolete, forcing you to rebuild from scratch. What blew me away about SkillOpt is how it bypasses the brute-force approach of modifying neural network weights. Instead, it treats the agent's execution document (skill.md) as a "trainable parameter" and beautifully replicates gradient descent directly within a pure text semantic space! I’ve done a deep dive into how this framework achieves zero inference-time cost and cross-generational portability without changing a single underlying weight. 👇 Check out my full breakdown and key takeaways in my latest article, Let me know your thoughts on this paradigm shift in the comments! medium.com/p/skillopt-buildi… #AIAgents #LLM #SkillOpt #MicrosoftResearch #GenerativeAI #BuildInPublic

Beyond LlamaParse & Unstructured.io? 🧐 We’ve been benchmarking Knowhere against the industry giants. The results? Our Tree-like semantic architecture consistently outperforms on retrieval accuracy while using 50% fewer tokens. Why? Because retrieval should be agent-native, not a flat search layer. We just open-sourced the Knowhere framework today———a retrieval + memory orchestration framework for AI agents and RAG systems. It’s powered by our own Tree-like semantic chunking architecture, designed specifically for deep document understanding. Watch how we handle complex document structures in the video below. 🎥👇 ⭐Star on GitHub: github.com/Ontos-AI/knowhere We also provide an installable plugin and a hosted API if you want to see the results in action immediately: 🔗 knowhereto.ai/?utm_source=x #AI #GenerativeAI #Python #OpenSource #Knowhere