jscott3201

jscott3201 / SeleneDB

Public

The AI-native graph database. Pure Rust, single binary, runs everywhere from a Raspberry Pi to a cloud VM.

ai ai-tools gql graphdatabase inmemory-db
10
0
100% credibility
Found Apr 11, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Rust
AI Summary

SeleneDB is a compact, pure Rust graph database designed for AI applications, offering pattern matching queries, vector search, time-series storage, and agent tools in a single binary.

How It Works

1
💡 Discover SeleneDB

You learn about SeleneDB, a simple tool that stores relationships between things like buildings and sensors, making AI helpers smarter and faster.

2
🚀 Get it running

Download the tiny program and start it on your laptop, tiny computer, or cloud machine with a single command.

3
📦 Add your data

Load your information about places, devices, and measurements using easy questions that create connections automatically.

4
🔍 Ask and explore

Pose natural questions to find hot rooms, connected equipment, or trends over time, seeing results instantly.

5
🤖 Supercharge with AI

Connect your AI assistants so they remember decisions, facts, and work across sessions without starting over.

✅ AI magic unlocked

Your system now powers smart agents that collaborate endlessly, saving time and tokens while solving real problems.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 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 SeleneDB?

SeleneDB is an AI-native graph database built in pure Rust as a single ~14MB binary that runs everywhere from a Raspberry Pi to a cloud VM with GPU acceleration. It handles property graphs with full ISO GQL queries, vector search, GraphRAG retrieval, agent memory stores, and time-series data—all optimized for AI workloads like cutting token waste in agent sessions. Developers get a drop-in server with QUIC/HTTP/MCP endpoints, Docker images, and CLI tools for quick prototyping.

Why is it gaining traction?

In the AI-native development scene on GitHub, it stands out by baking intelligence into the core: on-device embeddings, 64 MCP tools for agents (like graph-aware search and batch ingest), and 80-97% token savings on context recall via graph lookups. No C++ deps mean trivial deploys across edge and cloud, with sub-second cold starts and federation over QUIC. Early adopters in AI-native Panaversity GitHub projects praise its agent memory and GraphRAG for real session continuity.

Who should use this?

AI agent builders integrating graph memory to slash LLM costs, IoT engineers modeling sensor hierarchies on Raspberry Pis, or React Native AI devs needing lightweight vector/graph backends. Ideal for smart building apps with time-series and containment queries, or anyone ditching bloated DBs for a single-binary graph server.

Verdict

Promising for niche AI-graph use cases, but at 10 stars and 1.0% credibility, it's pre-production—test thoroughly despite solid docs and benchmarks. Grab it if you need edge AI-native graphs now; otherwise, watch for maturity.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.