Market Trends
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 jobshttps://runcabinet.comIt runs locally and is installable via npm.
GitHub (open source): https://github.com/hilash/cabinetThis 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/rxd8BYnNWould 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
Show HN: Cabinet – Kb+LLM (Like Paperclip+Obsidian)
An open-source, local-first knowledge base for LLMs, integrating various data types (CSVs, PDFs, inline web apps) and supporting "bring your own agent" with heartbeats and jobs, positioned as "Paperclip+Obsidian" for LLMs.
View Origin LinkProduct Positioning & Context
AI Executive Synthesis
An open-source, local-first knowledge base for LLMs, integrating various data types (CSVs, PDFs, inline web apps) and supporting "bring your own agent" with heartbeats and jobs, positioned as "Paperclip+Obsidian" for LLMs.
Cabinet addresses a fundamental limitation of LLMs: their lack of dynamic, context-specific knowledge. By integrating a local-first, open-source knowledge base capable of ingesting diverse data types (CSVs, PDFs, inline web apps), Cabinet provides LLMs with a critical external memory. The "bring your own agent" model with heartbeats and jobs offers flexibility and control, empowering developers to customize AI behavior. This product taps into the growing trend of augmenting LLMs with structured data and agentic capabilities, moving beyond static training data. Its local execution and open-source nature appeal to privacy-conscious enterprises and developers seeking full control over their AI infrastructure, positioning it as a foundational component for advanced enterprise AI applications.
Community Voice & Feedback
No active discussions extracted yet.
Related Early-Stage Discoveries
Discovery Source
Hacker News Aggregated via automated community intelligence tracking.
Tech Stack Dependencies
No direct open-source NPM package mentions detected in the product documentation.
Media Tractions & Mentions
No mainstream media stories specifically mentioning this product name have been intercepted yet.
Deep Research & Science
No direct peer-reviewed scientific literature matched with this product's architecture.