Brief

The SQLite MCP Server is a new tool that allows AI agents to directly query local SQLite databases using natural language. This server provides read/write access to databases, enabling agents to ask questions conversationally, inspect schemas automatically, and perform data analysis without needing API keys or cloud services. It is designed for local development, rapid prototyping, and offline workflows, offering benefits like reduced latency and enhanced data privacy. AI

Garudust Agent has launched a new feature that allows users to chat with their documents without needing a separate vector database. The system utilizes SQLite's FTS5 with a trigram tokenizer for efficient full-text search, enabling quick ingestion and querying of PDFs, text files, and other document types. This approach simplifies the process of building a knowledge base or analyzing documents by integrating RAG capabilities directly into the agent. AI

A developer has created a local daemon called eideticd to address the issue of losing context in Claude Code sessions. This tool runs on macOS and Linux, capturing every message as an 'engram' in a local SQLite database with minimal latency. A companion Python package allows users to query this historical data, enabling AI models to recall past conversations and debugging efforts without sending data to the cloud. AI

Lodestone is a new system designed to help developers efficiently retrieve research papers from arXiv. It utilizes SQLite for fast data access and is specifically tailored for use with Claude Code, an AI assistant. The system aims to streamline the process of finding relevant academic literature for coding-related tasks. AI

A new SQLite graph database has been developed to document the reasoning and context behind AI-generated code. This project aims to map the relationships between various factors that influence when and why AI systems produce code. The goal is to provide a clearer understanding of the AI development process for code generation. AI

A developer built a private AI assistant to query their project management and Git history data using only local LLMs. The system leverages a Text-to-SQL approach, translating natural language questions into SQL queries executed against a local SQLite database. This method ensures all data remains on the user's machine, prioritizing privacy and avoiding cloud-based APIs. The assistant uses Ollama to run models like Qwen2.5-coder locally, with a system prompt that includes the database schema, sample values, and few-shot examples to guide the LLM in generating accurate SQL queries and summarizing results. AI

Simon Willison has released the first alpha version of Datasette Agent, a new AI assistant designed to interact with data stored in SQLite databases. This web application allows users to ask questions about their data and can be expanded with custom plugins. A live demo is available on agent.datasette.io. AI