lance

SeaweedFS is a distributed storage system for object storage (S3), file systems, Iceberg table buckets, and Lance vector buckets, designed to handle billions of files with O(1) disk access and effortless horizontal scaling.

Object-storage native graph database with branching and typed ontology

AI-Native & Cloud-Native FS: A high-performance file semantic layer for cloud object storage, integrated with high-speed cache. CNCF Sandbox Project.

Durable, searchable memory of your past agent sessions.

The cost efficiency of S3 with the speed of local RAM. A multi-tenant vector and full-text search engine featuring a tiered RAM -> NVMe -> S3 architecture for microsecond latency on top of object storage

Skardi is a self-improving context framework for ai agents

Lossless storage and search for AI agent sessions, across every agentic client.

Browse Lance tables from your local machine in a simple web UI. No database to set up. Mount a folder and go.

Integration between Lance and Ray for distributed data processing

One bucket, every index: open-source, AI-native data platform in Rust. Hybrid retrieval on object storage, plus reactive data (Live), graph, SQL, Postgres and durable agent runs. Preview.

Comparing LanceDB and Elasticsearch for full-text search and vector search performance

A maintained fork of lance-graph. A Fast graph query engine over Lance datasets, built on DataFusion with a CSR index.

LanceDB C# SDK

Incremental processing and maintaining data freshness with CocoIndex and LanceDB

Polars plugin for reading and writing Lance datasets

Prototype database for designing database kernel

Cocoindex-based code indexing service with HNSW, automatic disk compaction, MCP Server, periodic git pull, metrics push to MySQL, and space-efficient branch searching

High-performance C++23/Python sparse storage engine for PB-scale recommender system embeddings, Engram, MoE, and KV Cache. Features Hogwild! lock-free updates, slot-directory reads, AVX-512 SIMD, and Lance 2PC checkpointing. Jax, PyTorch are all available.

Inspect, query, and export Lance datasets from the command line

Business data as geometry that AI agents navigate: explainable anomaly detection, drift and chain investigation with no model training. Snapshot sessions, copy-free branches, Lance storage, MCP-ready.