cloneisyou

cloneisyou / HEVEC

Public

A Vector Database Powered by Homomorphic Encryption

14
1
100% credibility
Found Feb 04, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
C++
AI Summary

HEVEC enables real-time similarity search over fully encrypted vectors for privacy-preserving AI memory systems.

How It Works

1
🔍 Discover secure AI memory

You hear about a way to let your personal AI search your private notes, photos, and memories without anyone else seeing them.

2
🔐 Create your private vault

You set up a special secure storage space just for your AI's long-term memory, keeping everything hidden.

3
📤 Upload your memories

You add your personal documents, chat histories, or image descriptions as searchable items.

4
⚡ Start the magic search

With one simple launch, your encrypted memory bank goes live, ready for lightning-fast private searches.

5
🤖 Link your AI assistant

You connect your AI companion so it can privately pull relevant memories when you chat.

6
💬 Ask natural questions

You talk to your AI as usual, and it finds the best matches from your hidden memories.

✨ Enjoy private insights

Your AI gives spot-on, helpful responses using your data—fully private and super fast.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 14 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is HEVEC?

HEVEC is a GitHub vector database that runs similarity searches on fully encrypted vectors, keeping data and queries private from the server. Clients encrypt embeddings with homomorphic encryption before upload, and the server computes inner product, L2, or cosine scores without decryption—ideal for million-scale datasets in under 200ms. Built in C++ with Python and Node.js bindings, it includes an HTTP server you launch via a script and APIs for setup, insert, query, and private retrieval.

Why is it gaining traction?

Unlike standard GitHub vector stores like Pinecone or Weaviate, HEVEC eliminates plaintext exposure, solving the privacy bottleneck in personal AI where embeddings hold sensitive data like documents or screen history. It matches vector database benchmarks on Deep1M or LAION without trusted hardware, plus PIR for private payload fetches. Developers dig the real-time speed and post-quantum security via lattice crypto.

Who should use this?

Privacy engineers building personal AI agents or copilots that need encrypted long-term memory for multimodal embeddings. Teams evaluating vector database comparisons for compliance-heavy apps, like healthcare chatbots or local RAG systems. Node devs integrating into Electron apps for secure vector dev workflows.

Verdict

Promising niche player for encrypted vector search, but at 11 stars and 1.0% credibility, it's early-stage—docs are solid with examples, but expect bugs and no broad tests. Try for prototypes if privacy trumps maturity; otherwise, stick to established options until it stabilizes.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.