Skip to content
The Daily Repo

Egoist-Machines / LodeDB

World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated

Why this job: says: vector database; topics: rag, vector-database, embeddings, semantic-search, hybrid-search

What it does

LodeDB is great for local RAG; it's _extremely fast_, exact by default, in-process, and on-disk. We're the best drop-in durable memory backend for LangChain, LlamaIndex, and mem0: the most compact on disk, the fastest per single query, GPU-accelerated for batched search, and durable in about a millisecond per write. Point any of them at LodeDB instead of its default store. Over 17.5k documents, per framework default:

Get started

pip install "lodedb[embeddings]"
# vector store + built-in text embedding (ONNX, no PyTorch)
Maintenance
Active
Last commit 22 days ago
Stars
104
On GitHub
Licence
Apache-2.0
Allows business use
Downloads for
2 systems
Mac, Linux
Latest version
v2.3.1
Released 22 days ago
Built with
Python
50% of the code

Is it looked after?

Contributors
2
Last 90 days
Issues
74% closed
8 still open
Pull requests
90 merged
6 waiting
Releases
28
28 in the last year

Similar repos

Repos similar to this one
RepoStarsLast commitLicenceDownloads for
alibaba / zvec16,215todayApache-2.0Mac, Windows, Linux
qdrant / qdrant35,47919 days agoApache-2.0Mac, Windows, Linux
milvus-io / bootcamp2,45119 days agoApache-2.0No downloads
More: download files, languages, topics and project record

Download files, v2.3.1

  • Mac4 files, 6 downloads
  • Linux2 files, 4 downloads

All files on GitHub (opens in new tab)

Languages

  • Python 50%
  • Rust 45%
  • Swift 4%
  • C <1%

Topics

  • ann
  • clip
  • db
  • embeddings
  • gpu-acceleration
  • hybrid-search
  • image-search
  • ivf
  • local-first
  • multimodal
  • onnx
  • privacy

Project record

  • JobRAG and search
  • StatusListed
  • Commits211
  • Forks11
  • Watching2
  • Stars in 28 days+3
  • CreatedJun 14, 2026
  • First seen by usNov 7, 2026
  • CheckedNov 7, 2026

Type to search.

Try