Cabinet
Kb+LLM (Like Paperclip+Obsidian)
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
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
HN · launched Apr 5, 2026 · 16 upvotes (top 28%) · 0 views
Niche: knowledge management software · 95 launches, 7 in the last 7 days ▲ +17% · Explore this niche →
Category and tags
- Horizontal
- Search & retrieval
- Prosumer
- AI-native
- Commercial product
Visit website ↗ Source listing ↗
More like this: all 95 launches in knowledge management software →
Could you build this?
Yes It is an Electron or web-based knowledge base and local file manager that integrates standard RAG pipelines (parsing PDFs, CSVs) with LLM agent hooks.
Discussion
11 comments analyzed.
Competitors mentioned: Obsidian, Claude, Cabinet, Paperclip
Concerns raised: Closed source software security risks, Knowledge locked into single AI provider ecosystem, LLM memory implementations unclear and uncontrollable, LLMs remember unimportant details and over-index on them
Feature requests: Organization/team support with shared knowledge bases, Permissions system for collaborative use, Visual knowledge layer for inspection and control, Support for multiple AI providers (Claude, Codex, local models)
Competitors
Other products that read as similar to this one : 281 launches clear the similarity bar, closest 8 shown.
Attention rank: #83 of 282 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 156 days after the earliest competitor.
- DocMason · hn · 2026-04-04 · 11 upvotes · similarity 0.53
- Open KB: Open LLM Knowledge Base · hn · 2026-04-13 · 6 upvotes · similarity 0.48
- Local note engine uses LLM to organize notes into a knowledge graph · hn · 2026-05-24 · 11 upvotes · similarity 0.48
- Run LLMs in Docker for any language without prebuilding containers · hn · 2026-01-14 · 26 upvotes · similarity 0.46
- I'm tired of my LLM bullshitting. So I fixed it · hn · 2026-01-22 · 5 upvotes · similarity 0.43
- Cq · hn · 2026-03-23 · 225 upvotes · similarity 0.43
- Lathe · hn · 2026-06-07 · 402 upvotes · similarity 0.43
- Thrum · hn · 2026-11-09 · 6 upvotes · similarity 0.42
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.