Back to browse
Cabinet – Kb+LLM (Like Paperclip+Obsidian)

Cabinet – Kb+LLM (Like Paperclip+Obsidian)

by Hilash·Apr 5, 2026·16 points·11 comments

AI Analysis

●●SolidShip ItSolve My Problem

Markdown files on disk with AI agents, no database lock-in like Obsidian.

Strengths
  • Files live on disk with Git backing, zero vendor lock-in or subscriptions
  • Agent heartbeat system enables autonomous scheduled research and updates
  • npm installable and self-hosted, runs entirely local with your own keys
Weaknesses
  • AI knowledge base category is extremely crowded with established players
  • Early stage with unclear differentiation beyond markdown-on-disk philosophy
Category
Target Audience

Indie founders, developers, knowledge workers wanting local AI memory

Similar To

Obsidian · Paperclip · Mem

Post Description

Hi HN,

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

https://runcabinet.com

It runs locally and is installable via npm. GitHub (open source): https://github.com/hilash/cabinet

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 :] )

If useful: Waitlist for a hosted version: https://runcabinet.com/waitlist Discord (small, but growing): https://discord.gg/rxd8BYnN

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.

Hila

Similar Projects

Infrastructure●●Solid

VoidLLM – privacy-first LLM proxy (Go, self-hosted)

Zero-knowledge architecture means prompts never touch disk — unlike LiteLLM.

Solve My ProblemSlick
chrisremo85
342mo ago
AI/ML●●Solid

Open KB: Open LLM Knowledge Base

Compiled wiki beats query-time RAG with vectorless PageIndex retrieval for long PDFs.

Big BrainNiche Gem
mingtianzhang
621mo ago