danilop/semstash
Unlimited semantic storage for humans and AI agents
SemStash helps individuals and AI agents organize and retrieve all their digital content, from documents and images to audio and video, using natural language. You simply upload your files, and then describe what you're looking for to find it instantly, without needing exact filenames or folder structures. Anyone who manages a large volume of diverse digital assets and struggles with traditional file organization would find this useful.
Use this if you need to store various types of digital content (text, images, video, audio) and want to find specific items by describing them naturally, rather than remembering exact keywords or locations.
Not ideal if you primarily work with highly structured data in databases or require advanced version control for code and documents.
Stars
9
Forks
—
Language
Python
License
MIT
Category
Last pushed
Dec 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/danilop/semstash"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
topoteretes/cognee
Knowledge Engine for AI Agent Memory in 6 lines of code
CaviraOSS/OpenMemory
Local persistent memory store for LLM applications including claude desktop, github copilot,...
verygoodplugins/automem
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory:
CortexReach/memory-lancedb-pro
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder...
divagr18/memlayer
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory...