Muratcan Koylan
@muratcan • 21,696 subscribers
Member of Technical Staff (Agents), Research @sullyai Building AI medical employees Prev/ AI Persona Development & Research @ 99Ravens
Videos
Since I posted my Personal OS / filesystem article, LLM personal knowledge bases have turned into a real topic in the AI world. I’ve been building this system in Cursor for almost two years, but I wasn’t expecting to end up talking with people like a YouTube co-founder, a NASCAR driver, or some of the AI leaders I respect most because of that post. For me it was the first signal that this wasn’t niche anymore. The biggest pushback on the article was whether a filesystem is enough or scalable for something like this. Scaling the vault is easy; scaling curation and placement is not. Karpathy’s LLM Wiki published soon after with same thesis and it was an independent validation for me. "LLM incrementally builds and maintains a persistent wiki structured, interlinked markdown between you and the raw sources." Now there are tons of similar projects, different takes on the same idea. That’s good, I’m also evolving my own stack from what’s out in the open, and honestly, reframing the personal filesystem as a wiki is a smart move. I’m posting this because I think the harder problem is still the knowledge transfer pipeline. Designing a Personal OS (aka personal knowledge base) is the easy part. The architecture only starts to pay off when you fill it for years -not just posts you liked, but decision patterns, career and life details, half-formed thoughts, writing, the messy stuff. Getting all of that into the right markdown file, at the right time, in the right shape is still the bottleneck. I built a Chrome extension (Feed2Context, details in the article) that grabs a post with my notes from my feed, drops it into the filesystem, and my agents synthesize and route it. I also built OpenHome assistant as a voice pipeline from my room into the wiki. Plus a bunch of MCP hooks into my accounts. But orchestrating all these helpers gets exhausting. A lot of people suggested Obsidian but I'm mostly on Readwise CLI to pull from X, LinkedIn, arXiv, books, and news. It works well on mobile, and because it’s a CLI, agents can find what they need and push it into the filesystem. Skill registries help a lot, in the videos I’ve got flows like Readwise CLI + alphaXiv MCP for research papers: save a paper, agent pulls the full text, analyzes it, teaches me back. I’m also testing Zapier CLI, and waiting for especially the Triggers API, between things like Yutori or plain cron, keeping a personal wiki alive is still hard; nobody wants to be the cron job for their own life, so triggers might be part of the answer. TL;DR: A personal filesystem you control isn’t optional if you don’t want to rent your memory from one AI company. The open problem is keeping it fed and current. What I actually want is one solution that can watch my screen, hear my voice, read my accounts, and write into my Personal OS without me acting as the integration layer forever.
Muratcan Koylan76,272 views • 3 months ago
🔻My First GPT-4 Project 🔻 I can chat with thousands of pages fast and affordably. How? Let's try with the latest World Economic Forum report (2023 April) Built with OpenAI, Pinecone and 1. Upload the PDF and divide its text into chunks. 2. Store the embeddings in your VectorStore. 3. Connect your Chat GPT-4 and restrict it to providing answers solely from the given document. It's truly a game-changer for a no-coder.
Muratcan Koylan492,279 views • 3 years ago
OpenAI wants markdown structure. Anthropic prefers XML tags. Google emphasizes few-shot examples. So I built a simple agent system that reads the official prompting docs and applies them to the given prompt. Each optimizer runs a ReAct loop: - list_provider_docs → discover available guidelines - read_provider_doc → fetch specific content - submit_optimization → return structured result Agent decides what context it needs. The loop runs until submission: 1. LLM reasons about the task 2. Calls a tool 3. Observes result 4. Repeats Typically 3-4 iterations. Parallel execution via asyncio.gather; all providers optimize concurrently. Good to explore the agent design and prompts. Feel free to play with it. Shared the repo here:
Muratcan Koylan63,789 views • 7 months ago
I've built it for you!! It's an automated AI system that analyzes AI case studies (you can change the use case) to identify and document enterprise-level AI implementations. It starts by reading URLs from a CSV file and uses web scraping (either through WebLoader or Firecrawl) to extract the content from each case study. The extracted content is then sent to Claude 3.5 Sonnet, which analyzes whether the case study represents a genuine enterprise AI implementation based on specific criteria like company maturity, implementation scale, and measurable business outcomes. For each URL, the system first saves the raw content and then performs this initial qualification analysis. If Claude determines that a case study qualifies as an enterprise AI implementation, the system proceeds to generate a detailed analysis. It creates three types of reports: - an individual case study report with sections like Executive Summary, AI Strategy Analysis, and Business Impact Assessment - a cross-case analysis that identifies patterns and trends across multiple case studies - and an executive dashboard summarizing key metrics and insights. All of these reports are saved in structured formats (markdown for individual reports, JSON for cross-case analysis and dashboard) in their respective directories. If a case study doesn't qualify as an enterprise AI implementation, the system logs the reason and moves on to the next URL. The entire process is asynchronous and provides detailed terminal feedback about its progress and decisions.
Muratcan Koylan85,319 views • 1 year ago
No more content to load