DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.
1,180+ deals tracked · 22 AI investment memos · Updated daily
Show HN: Cabinet – Kb+LLM (Like Paperclip+Obsidian)
Hi HN,<p>for quite some time I've been thinking how LLMs are missing the knowledge base, where I can dump CSVs, PDFs, and most important, inline web app. running on Claude Code (bring your own agent) with agents with heartbeats and jobs<p><a href="https://runcabinet.com" rel="nofollow">https://runcabinet.com</a><p>It runs locally and is installable via npm. GitHub (open source): <a href="https://github.com/hilash/cabinet" rel="nofollow">https://github.com/hilash/cabinet</a><p>This is still very early. I put the first version together quickly after seeing a post by Andrej Karpathy about LLM knowledge bases, which matched closely with what I’d been building. Some people have already started trying it and opening PRs, which has been encouraging (got 374 stars in 2 days :] )<p>If useful: Waitlist for a hosted version: <a href="https://runcabinet.com/waitlist" rel="nofollow">https://runcabinet.com/waitlist</a> Discord (small, but growing): <a href="https://discord.gg/rxd8BYnN" rel="nofollow">https://discord.gg/rxd8BYnN</a><p>Would really appreciate feedback: does this “KB + agents” model make sense? what would you expect from a system like this? where does this fall apart? Happy to answer anything.<p>Hila
Cabinet captures a high-growth niche by combining local-first knowledge bases with agentic workflows, a direction recently validated by industry leaders like Andrej Karpathy. The project shows exceptional early developer traction (374 stars in 2 days), though it faces significant competition and 'feature-not-a-product' risk from major LLM providers.