# libSQL Published articles for libSQL. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Building a Retrieval Pipeline with Turso and Voyage AI DevFeed: [Building a Retrieval Pipeline with Turso and Voyage AI]() Original publisher: [Read original article]() Author: Jeff Olson Published: 2026-07-15T00:00:00Z Content type: tutorial Language: en Sources: [Turso Blog]() Topics: [Turso](), [Retrieval Augmented Generation (RAG)](), [Databases](), [Embeddings](), [Artificial Intelligence](), [SQLite](), [API](), [Benchmark]() Tags: [api](), [benchmark](), [database](), [embedding](), [embeddings](), [libsql](), [memory](), [performance](), [rag](), [retrieval](), [sql](), [sqlite](), [turso](), [vector](), [work]() ### AI overview This article presents a retrieval-plus-memory architecture for AI agents using Turso as an embeddable SQLite-compatible database with native vector search and Voyage AI for embedding and reranking. It covers data modeling, retrieval, agent memory, performance, and cost considerations. ### Source excerpt A retrieval-plus-memory loop for AI agents that collapses the usual multi-service RAG stack into one embeddable Turso database and the Voyage AI API. ## Turso Sync: a much, much, much better way to sync DevFeed: [Turso Sync: a much, much, much better way to sync]() Original publisher: [Read original article]() Author: Glauber Costa Published: 2026-04-24T00:00:00Z Content type: comparison Language: en Sources: [Turso Blog]() Topics: [Database]() Tags: [embedded-replicas](), [libsql](), [performance](), [replication](), [rust](), [sqlite](), [sync](), [turso]() ### AI overview The article recommends Turso Sync over libSQL Embedded Replicas for synchronized local databases. It contrasts CDC-based logical-change syncing with physical-page replication and reports up to 312x faster syncs with 18x less network traffic. ### Source excerpt Turso Sync uses CDC to ship logical changes, not physical pages. The result: up to 312x faster syncs and 18x less network traffic than Embedded Replicas. ## Carl Sverre ruined my day. And it was glorious DevFeed: [Carl Sverre ruined my day. And it was glorious]() Original publisher: [Read original article]() Author: Glauber Costa Published: 2026-04-23T00:00:00Z Content type: article Language: en Sources: [Turso Blog]() Topics: [Database]() Tags: [api](), [bugs](), [conference](), [database](), [embedded](), [libsql](), [serverless](), [sqlite](), [tool](), [turso](), [typescript]() ### AI overview Turso describes maintaining libSQL, a SQLite fork, while rewriting its database system and trying to keep native and pure-JavaScript TypeScript packages API-compatible. A new Antithesis tool reportedly found five bugs quickly, increasing confidence to ship. ### Source excerpt How a new tool from Antithesis helped us find 5 bugs in minutes and gave us the confidence to ship. ## Introducing the Turso Serverless JavaScript Driver DevFeed: [Introducing the Turso Serverless JavaScript Driver]() Original publisher: [Read original article]() Author: Pekka Enberg Published: 2025-07-31T00:00:00Z Content type: release Language: en Sources: [Turso Blog]() Topics: [Turso](), [Serverless](), [JavaScript](), [Cloudflare Workers](), [Cloudflare](), [Vercel](), [libSQL](), [Deno](), [SQLite](), [Highlight.js](), [Discord]() Tags: [api](), [cloudflare](), [cloudflare-workers](), [compatibility](), [edge-compute](), [experimental](), [fetch](), [javascript](), [libsql](), [performance](), [serverless](), [sqlite](), [switching](), [turso](), [vercel]() ### AI overview Turso introduces an experimental, fetch-only Serverless JavaScript Driver for connecting to Turso databases from serverless and edge environments that do not support TCP connections, including Cloudflare Workers, Vercel Edge Functions, and Deno Deploy. It provides a shared API with the LibSQL client so applications can switch between local embedded databases and remote edge deployments with minimal code changes. ### Source excerpt Connect to Turso from serverless and edge environments with our new fetch-only JavaScript driver, designed for Cloudflare Workers, Vercel Edge Functions, and more. ## Turso Cloud Works with Capacitor DevFeed: [Turso Cloud Works with Capacitor]() Original publisher: [Read original article]() Author: Jamie Barton Published: 2025-07-28T00:00:00Z Content type: news Language: en Sources: [Turso Blog]() Topics: [Turso](), [SQLite](), [Mobile](), [Cloud](), [Databases](), [SQL]() Tags: [android](), [cli](), [ios](), [libsql](), [mobile](), [mobile-apps](), [offline](), [sql](), [sqlite](), [sync](), [turso]() ### AI overview Turso Cloud is now supported in Capacitor mobile apps through the @capawesome/capacitor-libsql plugin, enabling offline-first applications with synchronization between local SQLite files and Turso Cloud. ### Source excerpt Today we are excited to announce that Capacitor now supports Turso Cloud with the new @capawesome/capacitor-libsql plugin. ## New SDKs for Python and SQLAlchemy DevFeed: [New SDKs for Python and SQLAlchemy]() Original publisher: [Read original article]() Author: Levy Albuquerque Published: 2025-06-10T00:00:00Z Content type: release Language: en Sources: [Turso Blog]() Topics: [SDKs](), [migration]() Tags: [aws](), [database](), [drivers](), [fly-io](), [github](), [libsql](), [migration](), [python](), [sdks](), [sqlalchemy](), [turso]() ### AI overview Turso announces official Python SDKs for libsql and SQLAlchemy. Users should upgrade before older websocket-based drivers stop working after the stated migration deadline. ### Source excerpt Turso ships new official Python SDKs: 'libsql' and 'sqlalchemy-libsql'. Upgrade before June 18 when older websocket-based drivers stop working on AWS. ## Powering AI Agents: VoltAgent & Turso for Global, Low-Latency Memory DevFeed: [Powering AI Agents: VoltAgent & Turso for Global, Low-Latency Memory]() Original publisher: [Read original article]() Author: Omer Aplak, CEO at VoltAgent Published: 2025-05-26T00:00:00Z Content type: article Language: en Sources: [Turso Blog]() Topics: [AI Bots]() Tags: [agents](), [ai](), [ai-agents](), [databases](), [global](), [latency](), [libsql](), [low-latency](), [memory](), [sqlite](), [turso]() ### AI overview The article explains how VoltAgent and Turso provide persistent, low-latency memory for AI agents using LibSQL and SQLite databases near users. ### Source excerpt How VoltAgent pairs with Turso to give AI agents global, low-latency memory using LibSQLStorage and per-user SQLite databases placed close to your users. ## We will rewrite SQLite. And we are going all-in DevFeed: [We will rewrite SQLite. And we are going all-in]() Original publisher: [Read original article]() Author: Glauber Costa Published: 2025-01-21T00:00:00Z Content type: article Language: en Sources: [Turso Blog]() Topics: [SQLite](), [Rust](), [Database](), [libSQL](), [Open Source](), [Turso]() Tags: [announcement](), [architecture](), [database](), [github](), [libsql](), [open-source](), [rust](), [sqlite](), [turso]() ### AI overview Turso explains its decision to rewrite SQLite from scratch in Rust with a modern asynchronous architecture after concluding that libSQL had not achieved the original goal of evolving SQLite's core through community contributions. The new project has attracted contributors and foundational database work, motivating Turso to make it an official focus. ### Source excerpt Why we are rewriting SQLite from scratch in Rust instead of evolving libSQL, and going all-in on an async, open contribution database for the next decade. ## Announcing Laravel Support and PHP PDO Interface DevFeed: [Announcing Laravel Support and PHP PDO Interface]() Original publisher: [Read original article]() Author: Levy Albuquerque Published: 2025-01-09T00:00:00Z Content type: release Language: en Sources: [Turso Blog]() Topics: [Laravel](), [Turso](), [PHP](), [libSQL](), [PHP Data Objects (PDO)](), [Composer](), [Eloquent ORM](), [Object-relational mapping](), [SQLite](), [Embeddings](), [Query (disambiguation)](), [migration]() Tags: [database](), [embeddings](), [features](), [laravel](), [libsql](), [orm](), [php](), [recommendation-system](), [sdk](), [sdks](), [sqlite](), [turso]() ### AI overview Turso announces official Laravel support through the open-source libsql-laravel adapter and PHP PDO interface. The technical preview integrates with Laravel's database layer, supports local SQLite and Turso configurations, and removes the need for custom PHP extensions. The article also demonstrates migrations, Eloquent models, vector embeddings, and similarity searches for a movie recommendation system. ### Source excerpt Use Turso natively with Laravel through our new 'libsql-laravel' adapter and PHP PDO interface. No custom PHP extensions, just a database URL and auth token. ## Add comments to your Astro blog with AstroDB and Turso DevFeed: [Add comments to your Astro blog with AstroDB and Turso]() Original publisher: [Read original article]() Author: Jamie Barton Published: 2024-12-12T00:00:00Z Content type: tutorial Language: en Sources: [Turso Blog]() Topics: [Astro](), [Turso](), [Database](), [libSQL](), [SQLite](), [Tailwind CSS](), [Platform API](), [Template]() Tags: [astro](), [database](), [go](), [libsql](), [sqlite](), [tailwind](), [turso](), [tutorial]() ### AI overview This tutorial shows how to add a commenting system to an Astro blog using Astro Actions, Server Islands, AstroDB, libSQL, and Turso. It covers creating a blog from a template, configuring and seeding a SQLite database, fetching and displaying comments, styling them with Tailwind, and accepting new comments through form submissions. ### Source excerpt Turn your static blog into a dynamic one by adding comments with AstroDB, Astro Actions, and Turso. ## Introducing Limbo: A complete rewrite of SQLite in Rust DevFeed: [Introducing Limbo: A complete rewrite of SQLite in Rust]() Original publisher: [Read original article]() Author: Pekka Enberg Published: 2024-12-10T00:00:00Z Content type: article Language: en Sources: [Turso Blog]() Topics: [SQLite](), [Rust](), [libSQL](), [Turso]() Tags: [fork](), [libsql](), [memory-safe](), [rust](), [sqlite](), [turso]() ### AI overview The article introduces Limbo, an ambitious project to completely rewrite SQLite in Rust. It contrasts this approach with libSQL's earlier fork of SQLite and discusses goals such as memory safety, compatibility, easier evolution, and support for changes like asynchronous I/O. ### Source excerpt we forked SQLite with the libSQL project. What would it be like if we just rewrote it? ## Filtering in Vector Search with Metadata and RAG Pipelines DevFeed: [Filtering in Vector Search with Metadata and RAG Pipelines]() Original publisher: [Read original article]() Author: Volodymyr Pavlyshyn Published: 2024-11-11T00:00:00Z Content type: tutorial Language: en Sources: [Turso Blog]() Topics: [AI search](), [Language models](), [AI Bots]() Tags: [agents](), [ai](), [ai-agents](), [database](), [embeddings](), [large-language-models-llms](), [libsql](), [rag](), [retrieval](), [retrieval-augmented-generation](), [search](), [sqlite](), [vector]() ### AI overview The article explains how to combine vector search with structured metadata filters in RAG pipelines. It describes libSQL's vector storage and indexing, along with pre-filtering, post-filtering, and CTE-based query optimization. ### Source excerpt How Kin combines libSQL vector search with metadata filters to build RAG pipelines: pre-filtering, post-filtering, and CTE-based query patterns explained. ## You Don't Need A Separate Vector Database DevFeed: [You Don't Need A Separate Vector Database]() Original publisher: [Read original article]() Author: Jamie Barton Published: 2024-11-04T00:00:00Z Content type: opinion Language: en Sources: [Turso Blog]() Topics: [Databases](), [Turso](), [libSQL](), [AI search](), [Embeddings](), [Retrieval Augmented Generation (RAG)](), [SQLite](), [SQL]() Tags: [architecture](), [data](), [database](), [databases](), [embeddings](), [full-text-search](), [libsql](), [rag](), [search](), [sql](), [sqlite](), [turso](), [vector]() ### AI overview The article argues that many applications do not need a separate vector database. Modern databases can combine vector search with SQL, full-text search, application data, caching, and background jobs, reducing synchronization and operational complexity. It presents Turso's native libSQL vector datatype as one way to store vectors alongside regular data, while acknowledging that specialized vector databases may still be justified when their additional features are required. ### Source excerpt Why you can skip Pinecone and friends: modern databases like Turso ship native vector search alongside SQL, full-text, and your application data in one place. ## Turso Goes Mobile With Official iOS & Android SDKs DevFeed: [Turso Goes Mobile With Official iOS & Android SDKs]() Original publisher: [Read original article]() Author: Glauber Costa Published: 2024-10-22T00:00:00Z Content type: article Language: en Sources: [Turso Blog]() Topics: [Turso](), [Mobile](), [SDKs](), [Android](), [iOS](), [Embedded Replicas](), [libSQL](), [React Native](), [SQLite](), [Flutter]() Tags: [ai](), [android](), [embedded-replicas](), [flutter](), [ios](), [libsql](), [mobile](), [offline](), [on-device](), [react-native](), [sdks](), [sqlite](), [sync](), [turso](), [vector]() ### AI overview Turso introduces official mobile SDKs for iOS with Swift, Android with Kotlin, and React Native for cross-platform development. The SDKs bring Turso and libSQL capabilities such as embedded replicas, offline synchronization, encryption at rest, and vector search to mobile applications, with community support also available for Flutter. ### Source excerpt Learn about what's new with Turso's official mobile SDKs for Launch Week Day 2. ## Turso: Databases For All Your AI Apps DevFeed: [Turso: Databases For All Your AI Apps]() Original publisher: [Read original article]() Author: Glauber Costa Published: 2024-10-21T00:00:00Z Content type: news Language: en Sources: [Turso Blog]() Topics: [Turso](), [Databases](), [AI Development](), [AI Agent](), [libSQL](), [Platform API](), [LangChain](), [Local-First](), [quantization](), [iOS](), [Mobile]() Tags: [agents](), [ai](), [databases](), [ios](), [langchain](), [libsql](), [local-first](), [platform-api](), [quantization](), [turso]() ### AI overview Turso announces generally available native vector search with DiskANN indexing, the Turso Vector SDK, 1-bit quantization, and LangChain support for libSQL as a vector store. The article also describes ephemeral database workflows for AI agents and privacy-focused local-first applications. ### Source excerpt On Day 1 of our Launch Week, find out why Turso is the database for all your AI apps. ## Local first AI assistant Kin leverages Turso's libSQL for on-device native Vector Search DevFeed: [Local first AI assistant Kin leverages Turso's libSQL for on-device native Vector Search]() Original publisher: [Read original article]() Author: Simon Westh Henriksen Published: 2024-10-21T00:00:00Z Content type: article Language: en Sources: [Turso Blog]() Topics: [libSQL](), [Turso](), [Local-First](), [Artificial Intelligence](), [AI search](), [Embeddings](), [Retrieval Augmented Generation (RAG)](), [SQLite](), [Mobile](), [Latency]() Tags: [ai](), [embeddings](), [libsql](), [local](), [local-first](), [mobile](), [on-device](), [rag](), [react](), [sqlite](), [vector-search]() ### AI overview Kin is a privacy-focused, local-first AI assistant that keeps user data on-device. The article explains why its developers chose Turso's libSQL, a SQLite-compatible database with native vector embeddings, to support on-device vector search and retrieval-augmented generation while reducing dependence on cloud servers and network latency. ### Source excerpt When Kin decided to build a privace focused, local first AI assistant, they settled on Turso's libSQL to power it. ## The space complexity of vector indexes in LibSQL DevFeed: [The space complexity of vector indexes in LibSQL]() Original publisher: [Read original article]() Author: Volodymyr Pavlyshyn Published: 2024-10-03T00:00:00Z Content type: article Language: en Sources: [Turso Blog]() Topics: [libSQL](), [ann](), [Graphs](), [Compression](), [Optimization](), [Database](), [Latency]() Tags: [ann](), [compression](), [env-file-security](), [graphs](), [latency](), [libsql](), [optimization](), [storage](), [vector]() ### AI overview This article examines the storage complexity of libSQL vector indexes based on the graph-based FreshDiskANN algorithm. It explains how graph storage and neighbor vectors increased a database from 3.5 MB to 50 MB, then discusses compression and max-neighbor settings for reducing space while balancing search speed and accuracy. ### Source excerpt How Kin shrunk libSQL's LM-DiskANN vector index storage on mobile by tuning compress_neighbors and max_neighbors, trading a little recall for big space wins. ## Building Vector Search and Personal Knowledge Graphs on Mobile with libSQL and React Native DevFeed: [Building Vector Search and Personal Knowledge Graphs on Mobile with libSQL and React Native]() Original publisher: [Read original article]() Author: Volodymyr Pavlyshyn Published: 2024-10-02T00:00:00Z Content type: article Language: en Sources: [Turso Blog]() Topics: [AI search]() Tags: [ai-agent](), [graphs](), [libsql](), [local-first](), [mobile](), [on-device](), [rag](), [react-native](), [search](), [vector]() ### AI overview Kin describes building on-device vector search and personal knowledge graphs for a React Native mobile AI application using libSQL. ### Source excerpt How Kin built on-device vector search and personal knowledge graphs for iOS and Android using libSQL bindings and React Native, with no cloud dependency. ## Personal Knowledge Graphs in AI RAG-powered Applications with libSQL DevFeed: [Personal Knowledge Graphs in AI RAG-powered Applications with libSQL]() Original publisher: [Read original article]() Author: Volodymyr Pavlyshyn Published: 2024-09-30T00:00:00Z Content type: article Language: en Sources: [Turso Blog]() Topics: [libSQL](), [Retrieval Augmented Generation (RAG)](), [Graphs](), [Embeddings](), [Local-First](), [Mobile](), [SQLite](), [Databases](), [Artificial Intelligence]() Tags: [ai](), [databases](), [embeddings](), [graphs](), [libsql](), [local-first](), [mobile](), [rag](), [sqlite]() ### AI overview The article explains how Kin uses libSQL in a local-first mobile AI application to store personal knowledge graphs and vector embeddings in an embeddable SQLite-compatible database. It describes the need to combine graph and vector capabilities, avoid synchronization costs across separate storage systems, and retain compatibility while adding vector search for RAG. ### Source excerpt How Kin uses libSQL on mobile to store personal knowledge graphs alongside vector embeddings, powering local-first RAG with one embeddable SQLite file. ## Processing embeddings with libSQL, Redpanda Kafka, and Mixedbread DevFeed: [Processing embeddings with libSQL, Redpanda Kafka, and Mixedbread]() Original publisher: [Read original article]() Author: Jamie Barton Published: 2024-09-19T00:00:00Z Content type: tutorial Language: en Sources: [Turso Blog]() Topics: [Embeddings](), [Kafka](), [Turso](), [libSQL](), [API](), [Serverless](), [SQLite](), [Database](), [CRUD]() Tags: [ai](), [async](), [embeddings](), [kafka](), [libsql](), [serverless](), [stream](), [turso](), [tutorial](), [workflow]() ### AI overview This tutorial explains how to build an asynchronous embedding pipeline with libSQL, Turso, Redpanda Kafka, and Mixedbread. It shows how to decouple embedding generation from an API or web application, stream database changes to Kafka, and store and query embeddings using Turso's native vector support. ### Source excerpt Build an async embedding pipeline using libSQL, Redpanda Kafka, and Mixedbread. Offload embedding generation from your API and stream results into Turso. ## Why Prisma chose Turso to power Prisma Optimize DevFeed: [Why Prisma chose Turso to power Prisma Optimize]() Original publisher: [Read original article]() Author: Pierre-Antoine Urvoy Published: 2024-09-18T00:00:00Z Content type: article Language: en Sources: [Turso Blog]() Topics: [data-processing](), [AI Chat](), [Temporal data](), [Node.js]() Tags: [ai](), [analysis](), [conversational-ai](), [database](), [libsql](), [node-js](), [open-source](), [orm](), [prisma](), [sqlite](), [turso](), [typescript]() ### AI overview Prisma explains why it selected Turso as the data-storage backbone for Prisma Optimize, emphasizing on-demand database provisioning, SQLite and libSQL compatibility, vendor flexibility, and multi-schema deployments. Prisma Optimize records application queries, analyzes them, and offers performance recommendations plus a conversational AI assistant. ### Source excerpt When Prisma decided to build Prisma Optimize, they settled on Turso to power it. Here's why. ## Goodbye Studio, Hello DB DevFeed: [Goodbye Studio, Hello DB]() Original publisher: [Read original article]() Author: Fred Schott Published: 2024-09-13T00:00:00Z Content type: article Language: en Sources: [The Astro Blog]() Topics: [Astro](), [Astro DB](), [libSQL](), [Turso](), [Databases]() Tags: [astro](), [astro-db](), [database](), [discord](), [libsql](), [sql](), [turso]() ### AI overview Astro is winding down Astro Studio, its hosted database platform, after failing to find product-market fit. Astro DB will instead connect to any libSQL database, including Turso, which Astro recommends as an alternative. Existing Astro Studio databases will become inaccessible after March 1, 2025 and will then be deleted. ### Source excerpt We have decided to wind down Astro Studio and open up Astro DB to connect to any libSQL database, including Turso. Read on to hear what comes next for Astro and Astro DB. ## Astro 4.15 DevFeed: [Astro 4.15]() Original publisher: [Read original article]() Author: Matthew Phillips; Erika; Ben Holmes Published: 2024-08-29T00:00:00Z Content type: release Language: en Sources: [The Astro Blog]() Topics: [Astro](), [Astro DB](), [libSQL](), [Back end](), [Internationalization (i18n)](), [Routing (disambiguation)]() Tags: [astro](), [astro-db](), [cli](), [javascript](), [libsql](), [migration](), [release](), [upgrade]() ### AI overview Astro 4.15 stabilizes Astro Actions, providing fully type-safe backend functions with data fetching, JSON parsing, and input validation. The release also adds libSQL remotes for Astro DB, improved i18n fallback routing, and a timeout option for client:idle. ### Source excerpt Astro 4.15 is now available! This release stabilizes Astro Actions -- our solution for fully type-safe backend functions. Also included: support for libSQL remotes in Astro DB, a new timeout option for `client:idle`, and more. ## Introducing the Turso Per-User Starter DevFeed: [Introducing the Turso Per-User Starter]() Original publisher: [Read original article]() Author: Jamie Barton Published: 2024-08-28T00:00:00Z Content type: article Language: en Sources: [Turso Blog]() Topics: [Turso](), [Multi-tenancy](), [Per-user Database](), [Boilerplate](), [libSQL](), [Next.js](), [SQLite](), [Drizzle](), [Software as a service](), [GitHub](), [Discord](), [Demo]() Tags: [discord](), [drizzle](), [github](), [libsql](), [multi-tenancy](), [next-js](), [orm](), [saas](), [sqlite](), [turso](), [tutorial]() ### AI overview Turso introduces a Per-User Starter boilerplate for building scalable multi-tenant SaaS applications with Next.js, Clerk, Drizzle, and Turso. It uses Turso's multi-database schemas to support database-per-user or database-per-tenant architectures, with libSQL enabling consistent local, cloud, edge, and infrastructure deployments. ### Source excerpt Power Multi-Tenant Applications with Next.js, Clerk, Drizzle, and Turso [Next page]()