HN Showcase
Back to browse
Digger Solo – Local AI File Explorer

Digger Solo – Local AI File Explorer

by sean_pedersen·Jun 4, 2026·5 points·0 comments
Visit ProjectView on HN

AI Analysis

●MidEye CandyCozy

Semantic file maps look cool but require external LLM API keys despite local claims.

Strengths
  • •Semantic map visualization clusters related files by content similarity
  • •Duplicate detection finds near-identical files even with different filenames
  • •Files never leave your machine for the core search and mapping features
Weaknesses
  • •LLM chat requires external OpenAI-compatible API key, undermining 100% local claim
  • •Semantic search and RAG are now table stakes—Everything.ai and others do this
Category
Productivity
Target Audience

Knowledge workers with large local file collections who want semantic search

Similar To

Everything.ai · Fileside · Raycast

Post Description

After a lot of work I present Digger Solo 0.5.0 - the AI file explorer that respects your privacy (everything runs locally).

Demo video: https://vimeo.com/1198414414

New features: - LLM Chat with RAG (bring your own OpenAI compatible API key - ideally host a local model) - fresh redesign with light theme available in settings - multi-tabbed GUI: open multiple semantic maps at once - smart music player: auto-plays similar songs

Digger Solo offers semantic search and maps that allow you to browse your files intuively - uncovering hidden connections and near duplicates easily.

Happy to answer questions.

Similar Projects

AI/ML●●Solid

I built proxy that keeps RAG working while hiding PII

Consistent pseudonymization beats redaction when RAG embeddings must survive.

Big BrainSolve My Problem
rohansx
403mo ago
AI/ML●Mid

Is the "frozen weights" paradigm the main bottleneck for AGI?

The repo openly rejects the 'frozen weights' assumption and tries to prototype an assistant that rewires online — you can see the scaffolding in files like autonomous_ai.py, view_graph.py, a configs folder, a streamlit_apps dir and chroma_data. That's an interesting, contrarian direction, but the project is clearly early-stage: the UI and repo layout are tidy, yet there’s little in-repo evidence of benchmarks, experiments, or reproducible results to back the big claim.

Bold BetRabbit Hole
8lamaster8
104mo ago
AI/ML●Mid

RAG built for Frappe using TurboVec

RAG for Frappe when LangChain and LlamaIndex already support custom integrations.

Ship It
nathaah3
206d ago