HN Showcase
Back to browse
GitHub Repository

Self-hostable RAG and semantic search infrastructure. High-performance, low-cost, and up in minutes.

0 starsGo

RagPack – Lightweight self-hosted RAG infra for startups

by emrecodes·Jul 6, 2026·2 points·0 comments
Visit ProjectView on HN

AI Analysis

●MidShip It

Yet another self-hosted RAG stack when Dify and AnythingLLM already exist.

Strengths
  • •~20MB idle memory footprint is genuinely low for a full RAG stack
  • •npx ragpack start command gets stack running in minutes with no config
  • •Supports Ollama for fully local inference without cloud API calls
Weaknesses
  • •0 stars and 3 issues on GitHub signals very early stage with unknown stability
  • •RAG infrastructure is crowded with Dify, LangChain, LlamaIndex, Flowise
Category
AI/ML
Target Audience

Startups adding semantic search to existing apps

Similar To

Dify · AnythingLLM · LlamaIndex

Similar Projects

AI/ML●●Solid

Docker AI Stack, self-hosted LLM/STT/TTS/MCP in one compose file

One-command local AI stack bundling Ollama, Whisper, and MCP Gateway.

Ship ItCozy
hwdsl2
102mo ago
AI/ML●Mid

Docker AI Stack – Deploy 8 self-hosted AI services with one command

Yet another one-command AI stack when Ollama and Jan already exist.

Ship It
hwdsl2
101mo ago
Infrastructure●Mid

Aegis Sentinel – Self-healing infra engine using ML

Isolation Forest + a Recovery Engine that can manage Docker containers is the clearest, worthwhile idea here; structured JSON logs and pytest hints at attention to auditability and QA. The repo, however, reads like an ambitious prototype — few commits, placeholder clone URLs, and README rhetoric (EB-2 NIW mentions) outpaces the visible implementation — promising, but still early and derivative in a crowded auto-heal space.

Bold BetShip It
PkLavc
214mo ago