agent-first Archives

Tech Optimizer

May 13, 2026

Databricks Syncs Postgres to Lakehouse Natively

Databricks has introduced Native Lakehouse Sync, currently in public preview, which enables direct replication of data from Lakebase Postgres into Unity Catalog managed tables, simplifying data transfer without traditional pipeline complexities. This feature operates natively within Lakebase, utilizing its Write-Ahead-Log (WAL) and requiring minimal setup time. It does not negatively impact Postgres performance or incur additional costs, and schema changes are automatically propagated. Native Lakehouse Sync supports agent-first development by scaling down when idle and integrating monitoring functions. Data transferred to Unity Catalog is immediately accessible for AI-native analytics and benefits from unified governance features. Every data operation is captured as SCD Type 2 history by default, facilitating compliance and audit processes. The setup of Lakebase and activation of sync is quick, allowing existing and future tables to be available in Unity Catalog within a minute.

Tech Optimizer

May 1, 2026

Ghost: A Database for Our Times?

Ghost, developed by ghost.build, is an "agent-first" Postgres database platform designed for AI-related applications, allowing developers and AI agents to create, fork, inspect, query, manipulate, and delete databases easily. It is free to use and hosted on Ghost’s Cloud infrastructure, making it suitable for testing, prototyping, and disposable database environments. Users can create databases on demand, execute SQL queries, and discard them when finished, contrasting with traditional managed databases. Ghost integrates with AI tools like Codex and Claude Code, providing direct database management capabilities through its MCP server. To install Ghost, users need a supported coding agent and a GitHub account. Installation commands differ for Linux, macOS, and Windows. After installation, users can verify the Ghost MCP server and interact with it through their coding agents. Examples of using Ghost include creating a sales data database, utilizing Ghost CLI commands, and experimenting with databases through AI agents. Ghost allows for rapid database manipulation and is ideal for proofs of concept and experimentation, although caution is advised before using it for production data.

Tech Optimizer

April 28, 2026

Constructive Open Sources Agentic DB, the Postgres Memory Layer for AI Agents

Constructive has released agentic-db, an open-source Postgres database aimed at improving AI agents with features like persistent memory, structured knowledge, and hybrid retrieval. This database allows for efficient searching, filtering, and ranking of information, addressing inefficiencies associated with traditional markdown file storage. Key features of agentic-db include long-term memory, conversation tracking, a versioned registry for skills and tools, rules and policies for governance, task orchestration, and runtime observability. It is delivered as a single installable Postgres schema, indexed for multiple retrieval modes, and supports integration with various AI assistants through generated Agent Skills and CLIs. agentic-db is available under the MIT license for local use, with a cloud offering in development for secure, scalable solutions. Developers can access it on npm and GitHub.

AppWizard

March 30, 2026

Google Unveils AppFunctions to Connect AI Agents and Android Apps

Google has introduced early beta features for Android aimed at enhancing task-centric capabilities through an "agent-first" operating system. The key component is AppFunctions, a Jetpack API that allows developers to expose self-describing capabilities within their applications for seamless interaction with AI agents while prioritizing user privacy and performance by executing tasks on-device. AppFunctions operates similarly to backend capabilities declared via MCP cloud servers but runs locally on the device. Additionally, a UI automation platform has been introduced to assist users in performing complex tasks without requiring developer input. This platform allows users to complete tasks like placing pizza orders or coordinating rideshares through the Gemini Assistant. Privacy and user control are emphasized, with all interactions designed for on-device execution and mandatory confirmations for sensitive tasks. Currently, these features are in early beta and available exclusively on the Galaxy S26 series, with plans for broader deployment in Android 17.